{
  "notice": "bxzxxr MCP archive: a record of what public MCP servers declared when we listed them (we never call their tools). It is data, not a rating: nothing here says a server is safe, secure, verified or trustworthy, and a server can change after we looked. Secrets we detected are redacted; redacted tool lists are withheld and only their hash is shown.",
  "infrastructure": {
    "host": "framethrower.ai",
    "site": "framethrower.ai",
    "addresses": [
      {
        "address": "76.76.21.21",
        "endpoints": 513,
        "shared_infrastructure": true,
        "network": {
          "asn": 16509,
          "name": "AMAZON-02 - Amazon.com, Inc.",
          "prefix": "76.76.21.0/24",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "76.76.21.21"
        ],
        "first_seen": "2026-11-22T04:51:02.780Z",
        "last_seen": "2026-11-22T04:51:02.780Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Vercel",
        "evidence": "Server header \"Vercel\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "FrameThrower",
      "version": "1.2.0",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "Vercel",
      "strict-transport-security": "max-age=63072000"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 512,
      "sample": [
        {
          "id": "139",
          "url": "https://agentblueprint.ai/mcp",
          "server_name": "ai.agentblueprint/agent-blueprint",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:34:00.875Z"
        },
        {
          "id": "141",
          "url": "https://agentcv.ai/mcp",
          "server_name": "ai.agentcv/registry",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:34:00.875Z"
        },
        {
          "id": "207",
          "url": "https://alcock.ai/api/mcp",
          "server_name": "ai.alcock/arena",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:35:02.466Z"
        },
        {
          "id": "249",
          "url": "https://arabickeyboard.ai/mcp",
          "server_name": "ai.arabickeyboard/name-calligraphy",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:36:01.093Z"
        },
        {
          "id": "321",
          "url": "https://aviado.ai/api/mcp",
          "server_name": "ai.aviado/health",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:38:01.448Z"
        },
        {
          "id": "730",
          "url": "https://droneintelligence.ai/api/mcp",
          "server_name": "ai.droneintelligence/drone-intelligence",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:48:01.210Z"
        },
        {
          "id": "910",
          "url": "https://fukushi.ai/api/mcp",
          "server_name": "ai.fukushi/dictionary",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:53:00.885Z"
        },
        {
          "id": "1235",
          "url": "https://instabids.ai/api/agent/mcp",
          "server_name": "ai.instabids/instabids",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:58:00.936Z"
        },
        {
          "id": "1255",
          "url": "https://jasonlovell.ai/mcp",
          "server_name": "ai.jasonlovell/site",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:59:01.356Z"
        },
        {
          "id": "1418",
          "url": "https://listplus.ai/mcp",
          "server_name": "ai.listplus/listplus",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T05:03:00.741Z"
        },
        {
          "id": "1691",
          "url": "https://opencancer.ai/api/mcp",
          "server_name": "ai.opencancer/opencancer",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:44:04.042Z"
        },
        {
          "id": "1733",
          "url": "https://overwing.ai/mcp",
          "server_name": "ai.overwing/mcp",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:45:02.375Z"
        },
        {
          "id": "1765",
          "url": "https://pechincha.ai/mcp",
          "server_name": "ai.pechincha/deals",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:45:03.297Z"
        },
        {
          "id": "2148",
          "url": "https://shurco.ai/mcp",
          "server_name": "ai.shurco/llm-pricing",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:49:02.107Z"
        },
        {
          "id": "2448",
          "url": "https://stablenews.ai/mcp/news",
          "server_name": "ai.stablenews/news",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:50:04.002Z"
        },
        {
          "id": "2486",
          "url": "https://subpay.ai/mcp",
          "server_name": "ai.subpay/document-reader",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:50:05.173Z"
        },
        {
          "id": "2487",
          "url": "https://subpay.ai/invoice/mcp",
          "server_name": "ai.subpay/invoice-reader",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:51:08.332Z"
        },
        {
          "id": "2488",
          "url": "https://subpay.ai/find/mcp",
          "server_name": "ai.subpay/tool-finder",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:52:02.549Z"
        },
        {
          "id": "2516",
          "url": "https://synthfolk.ai/api/mcp",
          "server_name": "ai.synthfolk/directory",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:51:08.804Z"
        },
        {
          "id": "2582",
          "url": "https://graviti.thesingulariti.ai/api/mcp",
          "server_name": "ai.thesingulariti/graviti",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:52:02.948Z"
        }
      ]
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "ai.framethrower",
      "total": 0,
      "sample": []
    },
    "same_repository": {
      "repository_url": "https://github.com/framethrower-ai/framethrower-mcp",
      "total": 0,
      "sample": []
    },
    "note": "Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators."
  },
  "endpoint": {
    "id": "903",
    "server_name": "ai.framethrower/framethrower",
    "url": "https://framethrower.ai/api/mcp",
    "host": "framethrower.ai",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-22T04:51:02.780Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "e342f6bc223c86cb545c3af9e2d5292a8005186797e4b5e8bde3386a8bfece8b",
    "first_listed_at": "2026-11-21T04:51:01.138Z",
    "created_at": "2026-11-21T04:30:18.380Z",
    "resolved_addresses": [
      "76.76.21.21"
    ]
  },
  "server": {
    "name": "ai.framethrower/framethrower",
    "title": "FrameThrower",
    "description": "Film stills from 5,489 films, searchable by lighting, lens character, shot size, colour and mood.",
    "version": "1.0.0",
    "registry_status": "active",
    "repository_url": "https://github.com/framethrower-ai/framethrower-mcp",
    "website_url": "https://framethrower.ai/mcp",
    "published_at": "2026-08-12T13:27:50.570Z",
    "updated_at": "2026-08-12T13:27:50.570Z",
    "first_seen": "2026-11-21T04:30:17.699Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T14:51:07.774Z"
  },
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 2,
    "answered": 2,
    "answered_percent": 100,
    "avg_listing_latency_ms": 526,
    "first_check_in_window": "2026-11-21T04:51:01.138Z",
    "consecutive_failures_now": 0,
    "days": [
      {
        "day": "2026-11-21",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      },
      {
        "day": "2026-11-22",
        "checks": 1,
        "answered": 1,
        "last_state": "listed"
      }
    ]
  },
  "tool_list": {
    "sha256": "e342f6bc223c86cb545c3af9e2d5292a8005186797e4b5e8bde3386a8bfece8b",
    "tools": 17,
    "resources": 0,
    "prompts": 0,
    "first_seen": "2026-11-21T04:51:01.782Z",
    "tool_names": [
      "search_frames",
      "find_by_craft",
      "find_similar",
      "get_frame_details",
      "get_frame_image",
      "search_commercials",
      "search_commercial_shots",
      "get_commercial",
      "similar_commercials",
      "similar_commercial_shots",
      "commercials_profile",
      "commercials_stats",
      "search_animation_frames",
      "similar_animation_frames",
      "find_animation_titles",
      "get_animation_title",
      "get_animation_sequence"
    ],
    "declared": {
      "tools": [
        {
          "name": "search_frames",
          "description": "Search the FrameThrower cinematography reference library by concept, mood, color, composition, or scene. Returns reference frames with film/credits metadata, a preview image and a link to view on FrameThrower. For the full-resolution file or the precomputed depth map, call get_frame_image with the frame id.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "query"
            ],
            "properties": {
              "limit": {
                "type": "number",
                "maximum": 40,
                "minimum": 1
              },
              "query": {
                "type": "string",
                "description": "Natural-language description, e.g. \"neon-lit rainy street at night\""
              },
              "enhance": {
                "type": "boolean",
                "description": "Smart search, on by default: rewrites short queries (\"bear\") into the descriptive language the frames were indexed with, like the website. Set false to search the exact text."
              }
            }
          },
          "annotations": {
            "title": "Search film stills",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "find_by_craft",
          "description": "Find frames by specific cinematography craft attributes — lens character, shot size, visual style, setting, time of day, director, or year range. All optional; combine to narrow. Use this to refine a search precisely.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "properties": {
              "lens": {
                "type": "string",
                "description": "e.g. \"anamorphic\", \"spherical\", \"vintage_soft\""
              },
              "limit": {
                "type": "number",
                "maximum": 40,
                "minimum": 1
              },
              "setting": {
                "type": "string",
                "description": "\"interior\" or \"exterior\""
              },
              "director": {
                "type": "string"
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "shot_size": {
                "type": "string",
                "description": "e.g. \"closeup\", \"wide\", \"medium\""
              },
              "time_of_day": {
                "type": "string",
                "description": "e.g. \"night\", \"day\""
              },
              "visual_style": {
                "type": "string"
              }
            }
          },
          "annotations": {
            "title": "Find frames by cinematography attribute",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "find_similar",
          "description": "Find frames visually/semantically similar to a given frame id (from a prior result). Use this to pull more references like one the user shortlisted.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "frameId"
            ],
            "properties": {
              "limit": {
                "type": "number",
                "maximum": 40,
                "minimum": 1
              },
              "frameId": {
                "type": "string"
              }
            }
          },
          "annotations": {
            "title": "Find similar frames",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "get_frame_details",
          "description": "Get the full metadata, a preview image and the FrameThrower link for a single frame id. For the full-resolution file or the depth map (camera geometry for image generation), call get_frame_image.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "frameId"
            ],
            "properties": {
              "frameId": {
                "type": "string"
              }
            }
          },
          "annotations": {
            "title": "Get frame details",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "get_frame_image",
          "description": "One frame's image at a paid size, as a link valid for an hour: \"full\" = the original full-resolution file (5 credits), \"large\" = 1280px (2), \"depth\" = the precomputed depth map, ControlNet-ready (2). Search results show a preview only — use this when the user wants the actual image for a deck, document, download or an image-generation pipeline.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "frameId"
            ],
            "properties": {
              "size": {
                "enum": [
                  "full",
                  "large",
                  "depth"
                ],
                "type": "string",
                "description": "default full"
              },
              "frameId": {
                "type": "string"
              }
            }
          },
          "annotations": {
            "title": "Get a frame image",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "search_commercials",
          "description": "Find whole COMMERCIALS (TV / online spots) in FrameThrower's ads library by idea, story or brief (\"two rival neighbours outdo each other at Christmas\", \"a product demo told as a heist\") and/or by facts: brand, director, agency, production company, DP, editor, award show and level, year, industry, market, tone, genre, structure, season. Without a query it lists matching spots, award winners first. Returns each spot with brand, title, year, credits, best award, logline, a still and a link to watch it.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "properties": {
              "dp": {
                "type": "string",
                "description": "Director of photography"
              },
              "sort": {
                "enum": [
                  "relevance",
                  "awards",
                  "newest",
                  "oldest"
                ],
                "type": "string"
              },
              "tone": {
                "type": "string",
                "description": "funny, heartwarming, epic, emotional, absurd, dark, inspiring…"
              },
              "brand": {
                "type": "string",
                "description": "Advertiser, e.g. \"Nike\", \"Guinness\""
              },
              "genre": {
                "type": "string",
                "description": "comedy, drama, documentary, action…"
              },
              "limit": {
                "type": "number",
                "maximum": 30,
                "minimum": 1
              },
              "music": {
                "type": "string",
                "description": "Composer / track / music house"
              },
              "query": {
                "type": "string",
                "description": "The idea / story in plain words. Leave out to just filter."
              },
              "agency": {
                "type": "string",
                "description": "Creative agency, e.g. \"Wieden+Kennedy\""
              },
              "editor": {
                "type": "string"
              },
              "format": {
                "type": "string",
                "description": "live_action, animation_2d, animation_3d, stop_motion, cgi, mixed"
              },
              "market": {
                "type": "string",
                "description": "Country code: US, UK, FR, DE, BR, JP…"
              },
              "offset": {
                "type": "number",
                "maximum": 1000,
                "minimum": 0
              },
              "person": {
                "type": "string",
                "description": "Anyone credited, any role"
              },
              "season": {
                "type": "string",
                "description": "halloween, christmas, black friday, thanksgiving, new year, valentines, easter, mothers day, fathers day, back to school, summer, spring, pride, super bowl"
              },
              "awarded": {
                "type": "boolean",
                "description": "true = won or shortlisted at an award show"
              },
              "director": {
                "type": "string"
              },
              "industry": {
                "type": "string",
                "description": "Ad category: Auto, Beer, Spirits, Drinks, Food & QSR, Retail, Tech, Telecom, Finance & Insurance, Fashion & Luxury, Beauty & Personal care, Sport, Travel, Gaming, Health & Pharma, Media & Entertainment, Public service & NGO, Home, FMCG"
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "celebrity": {
                "type": "boolean"
              },
              "min_award": {
                "enum": [
                  "grand_prix",
                  "gold",
                  "silver",
                  "bronze",
                  "shortlist"
                ],
                "type": "string",
                "description": "Best award at least this level"
              },
              "structure": {
                "type": "string",
                "description": "narrative, montage, vignettes, problem_solution, demo…"
              },
              "award_show": {
                "type": "string",
                "description": "One of: Cannes Lions, Clio Awards, D&AD, Epica, AICP Awards, London International Awards, British Arrows, The One Show, El Ojo de Iberoamérica, Eurobest, Creative Circle, Effie Awards, Ciclope, Spikes Asia, ANDY Awards, ADC Awards, DGA Awards, Kinsale Sharks, shots Awards, New York Festivals, Webby Awards, Emmy (Outstanding Commercial), IPA Effectiveness Awards, AdFest, Dubai Lynx, ADC Europe, Young Director Award"
              },
              "award_year": {
                "type": "number"
              },
              "production": {
                "type": "string",
                "description": "Production company, e.g. \"MJZ\", \"Smuggler\""
              },
              "max_duration": {
                "type": "number",
                "description": "seconds"
              },
              "min_duration": {
                "type": "number"
              }
            }
          },
          "annotations": {
            "title": "Search commercials",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "search_commercial_shots",
          "description": "Find individual SHOTS inside commercials by what is in the frame (\"hand pouring beer in slow motion\", \"car drifting at night in the rain\", \"family laughing at a kitchen table\"), with shot tags (size, angle, setting, time of day, lighting, mood, people, product / logo visible) and any commercial-level filter (brand, director, agency, award show, year…). Each shot has its still, its tags and a link to the exact moment; with clips: true, also a short clip of just that shot.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "query"
            ],
            "properties": {
              "dp": {
                "type": "string",
                "description": "Director of photography"
              },
              "mood": {
                "type": "string"
              },
              "spot": {
                "type": "string",
                "description": "Only inside this commercial (its id, e.g. AD-0505)"
              },
              "brand": {
                "type": "string",
                "description": "Advertiser, e.g. \"Nike\", \"Guinness\""
              },
              "clips": {
                "type": "boolean",
                "description": "true = also return a short clip of each shot (1 credit per clip on top of the call). Ask only when the user wants to see the shots move."
              },
              "limit": {
                "type": "number",
                "maximum": 30,
                "minimum": 1
              },
              "query": {
                "type": "string",
                "description": "What the shot shows, as a description of one frame"
              },
              "agency": {
                "type": "string",
                "description": "Creative agency, e.g. \"Wieden+Kennedy\""
              },
              "market": {
                "type": "string",
                "description": "Country code: US, UK, FR, DE, BR, JP…"
              },
              "people": {
                "type": "string",
                "description": "women, men, kids, teens, adults, seniors (comma-separated = all of them)"
              },
              "season": {
                "type": "string",
                "description": "halloween, christmas, black friday, thanksgiving, new year, valentines, easter, mothers day, fathers day, back to school, summer, spring, pride, super bowl"
              },
              "awarded": {
                "type": "boolean",
                "description": "true = won or shortlisted at an award show"
              },
              "setting": {
                "type": "string",
                "description": "interior, exterior, studio_void or virtual_cg"
              },
              "director": {
                "type": "string"
              },
              "industry": {
                "type": "string",
                "description": "Ad category: Auto, Beer, Spirits, Drinks, Food & QSR, Retail, Tech, Telecom, Finance & Insurance, Fashion & Luxury, Beauty & Personal care, Sport, Travel, Gaming, Health & Pharma, Media & Entertainment, Public service & NGO, Home, FMCG"
              },
              "lighting": {
                "type": "string",
                "description": "natural, high_key, low_key, silhouette, chiaroscuro"
              },
              "per_spot": {
                "type": "number",
                "maximum": 20,
                "minimum": 1,
                "description": "Max shots from one commercial (default 3)"
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "min_award": {
                "enum": [
                  "grand_prix",
                  "gold",
                  "silver",
                  "bronze",
                  "shortlist"
                ],
                "type": "string",
                "description": "Best award at least this level"
              },
              "shot_size": {
                "type": "string",
                "description": "extreme_closeup, closeup, medium_closeup, medium, medium_wide, full, wide, extreme_wide, insert"
              },
              "award_show": {
                "type": "string",
                "description": "One of: Cannes Lions, Clio Awards, D&AD, Epica, AICP Awards, London International Awards, British Arrows, The One Show, El Ojo de Iberoamérica, Eurobest, Creative Circle, Effie Awards, Ciclope, Spikes Asia, ANDY Awards, ADC Awards, DGA Awards, Kinsale Sharks, shots Awards, New York Festivals, Webby Awards, Emmy (Outstanding Commercial), IPA Effectiveness Awards, AdFest, Dubai Lynx, ADC Europe, Young Director Award"
              },
              "production": {
                "type": "string",
                "description": "Production company, e.g. \"MJZ\", \"Smuggler\""
              },
              "time_of_day": {
                "type": "string",
                "description": "day, night, golden_hour, dusk, dawn…"
              },
              "camera_angle": {
                "type": "string",
                "description": "eye_level, low_angle, high_angle, overhead, aerial, pov, worms_eye, dutch"
              },
              "logo_visible": {
                "type": "boolean"
              },
              "text_on_screen": {
                "type": "boolean"
              },
              "black_and_white": {
                "type": "boolean"
              },
              "product_visible": {
                "type": "boolean"
              }
            }
          },
          "annotations": {
            "title": "Search shots in commercials",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "get_commercial",
          "description": "The full breakdown of one commercial by id: idea, logline, tagline, product, audience, every credit by role (director, agency, production company, DP, editor, music, post, sound, VFX), every award (show, year, level, category), craft numbers (shots, average shot length, cuts per minute, when the product / brand / emotional peak / end card land), the script with timings, and the shot list (caption, tags and still per shot; with clips: true, each shot's clip too).",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "id"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Commercial id, e.g. AD-0505"
              },
              "clips": {
                "type": "boolean",
                "description": "true = also return a short clip of each shot (1 credit per clip on top of the call). Ask only when the user wants to see the shots move."
              },
              "shots": {
                "type": "boolean",
                "description": "Include the shot list (default true)"
              },
              "stills": {
                "type": "boolean",
                "description": "Include each shot's still image (1 credit per shot). Leave off unless the user wants to see the shots."
              }
            }
          },
          "annotations": {
            "title": "Get a commercial",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "similar_commercials",
          "description": "Commercials like a given one — by STORY (similar idea, tropes and tone) or by LOOK (similar shots: light, framing, palette). Accepts the same filters as search_commercials to narrow (e.g. only award winners, only another brand).",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "id"
            ],
            "properties": {
              "by": {
                "enum": [
                  "story",
                  "look"
                ],
                "type": "string",
                "description": "default story"
              },
              "id": {
                "type": "string",
                "description": "Commercial id, e.g. AD-0505"
              },
              "tone": {
                "type": "string",
                "description": "funny, heartwarming, epic, emotional, absurd, dark, inspiring…"
              },
              "brand": {
                "type": "string",
                "description": "Advertiser, e.g. \"Nike\", \"Guinness\""
              },
              "limit": {
                "type": "number",
                "maximum": 20,
                "minimum": 1
              },
              "awarded": {
                "type": "boolean",
                "description": "true = won or shortlisted at an award show"
              },
              "industry": {
                "type": "string",
                "description": "Ad category: Auto, Beer, Spirits, Drinks, Food & QSR, Retail, Tech, Telecom, Finance & Insurance, Fashion & Luxury, Beauty & Personal care, Sport, Travel, Gaming, Health & Pharma, Media & Entertainment, Public service & NGO, Home, FMCG"
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "min_award": {
                "enum": [
                  "grand_prix",
                  "gold",
                  "silver",
                  "bronze",
                  "shortlist"
                ],
                "type": "string",
                "description": "Best award at least this level"
              }
            }
          },
          "annotations": {
            "title": "Find similar commercials",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "similar_commercial_shots",
          "description": "More shots that look like the given shot ids (from earlier results or a shot list) — the refine loop: \"more like #2\". Takes the same shot tags and commercial filters to steer.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "shot_ids"
            ],
            "properties": {
              "mood": {
                "type": "string"
              },
              "tone": {
                "type": "string",
                "description": "funny, heartwarming, epic, emotional, absurd, dark, inspiring…"
              },
              "brand": {
                "type": "string",
                "description": "Advertiser, e.g. \"Nike\", \"Guinness\""
              },
              "clips": {
                "type": "boolean",
                "description": "true = also return a short clip of each shot (1 credit per clip on top of the call). Ask only when the user wants to see the shots move."
              },
              "limit": {
                "type": "number",
                "maximum": 30,
                "minimum": 1
              },
              "people": {
                "type": "string",
                "description": "women, men, kids, teens, adults, seniors (comma-separated = all of them)"
              },
              "awarded": {
                "type": "boolean",
                "description": "true = won or shortlisted at an award show"
              },
              "setting": {
                "type": "string",
                "description": "interior, exterior, studio_void or virtual_cg"
              },
              "industry": {
                "type": "string",
                "description": "Ad category: Auto, Beer, Spirits, Drinks, Food & QSR, Retail, Tech, Telecom, Finance & Insurance, Fashion & Luxury, Beauty & Personal care, Sport, Travel, Gaming, Health & Pharma, Media & Entertainment, Public service & NGO, Home, FMCG"
              },
              "lighting": {
                "type": "string",
                "description": "natural, high_key, low_key, silhouette, chiaroscuro"
              },
              "shot_ids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "maxItems": 10,
                "minItems": 1
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "min_award": {
                "enum": [
                  "grand_prix",
                  "gold",
                  "silver",
                  "bronze",
                  "shortlist"
                ],
                "type": "string",
                "description": "Best award at least this level"
              },
              "shot_size": {
                "type": "string",
                "description": "extreme_closeup, closeup, medium_closeup, medium, medium_wide, full, wide, extreme_wide, insert"
              },
              "time_of_day": {
                "type": "string",
                "description": "day, night, golden_hour, dusk, dawn…"
              },
              "camera_angle": {
                "type": "string",
                "description": "eye_level, low_angle, high_angle, overhead, aerial, pov, worms_eye, dutch"
              },
              "logo_visible": {
                "type": "boolean"
              },
              "text_on_screen": {
                "type": "boolean"
              },
              "black_and_white": {
                "type": "boolean"
              },
              "product_visible": {
                "type": "boolean"
              }
            }
          },
          "annotations": {
            "title": "Find similar shots in commercials",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "commercials_profile",
          "description": "The track record of a brand, director, agency, production company, DP, editor or composer in FrameThrower's ads library: how many spots, which years, who they work with (clients, agencies, directors, production companies), awards by show, typical tones and genres, their best and most recent work — and, for directors / agencies / production companies with a public page, the researched profile (description, founded, HQ, website).",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "kind",
              "name"
            ],
            "properties": {
              "kind": {
                "enum": [
                  "brand",
                  "director",
                  "agency",
                  "production",
                  "dp",
                  "editor",
                  "edit_house",
                  "post",
                  "music",
                  "sound",
                  "vfx"
                ],
                "type": "string",
                "description": "brand, director, agency, production, dp, editor, edit_house, post, music, sound or vfx"
              },
              "name": {
                "type": "string"
              }
            }
          },
          "annotations": {
            "title": "Brand or credit profile",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "commercials_stats",
          "description": "Count and rank the ads library: how many commercials match a filter, broken down by any of brand, director, agency, production, dp, editor, music, industry, market, year, genre, structure, format, tone, trope, award_show, season. E.g. \"which agencies won the most Cannes Lions for car ads since 2015\" = fields [agency], award_show Cannes Lions, industry Auto, year_min 2015.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "fields"
            ],
            "properties": {
              "dp": {
                "type": "string",
                "description": "Director of photography"
              },
              "tone": {
                "type": "string",
                "description": "funny, heartwarming, epic, emotional, absurd, dark, inspiring…"
              },
              "brand": {
                "type": "string",
                "description": "Advertiser, e.g. \"Nike\", \"Guinness\""
              },
              "genre": {
                "type": "string",
                "description": "comedy, drama, documentary, action…"
              },
              "limit": {
                "type": "number",
                "maximum": 50,
                "minimum": 1
              },
              "music": {
                "type": "string",
                "description": "Composer / track / music house"
              },
              "agency": {
                "type": "string",
                "description": "Creative agency, e.g. \"Wieden+Kennedy\""
              },
              "editor": {
                "type": "string"
              },
              "fields": {
                "type": "array",
                "items": {
                  "enum": [
                    "brand",
                    "director",
                    "agency",
                    "production",
                    "dp",
                    "editor",
                    "edit_house",
                    "post",
                    "music",
                    "sound",
                    "vfx",
                    "industry",
                    "market",
                    "language",
                    "year",
                    "genre",
                    "structure",
                    "format",
                    "tone",
                    "trope",
                    "award_show",
                    "award_year",
                    "season",
                    "collection"
                  ],
                  "type": "string"
                },
                "maxItems": 6,
                "minItems": 1
              },
              "format": {
                "type": "string",
                "description": "live_action, animation_2d, animation_3d, stop_motion, cgi, mixed"
              },
              "market": {
                "type": "string",
                "description": "Country code: US, UK, FR, DE, BR, JP…"
              },
              "person": {
                "type": "string",
                "description": "Anyone credited, any role"
              },
              "season": {
                "type": "string",
                "description": "halloween, christmas, black friday, thanksgiving, new year, valentines, easter, mothers day, fathers day, back to school, summer, spring, pride, super bowl"
              },
              "awarded": {
                "type": "boolean",
                "description": "true = won or shortlisted at an award show"
              },
              "director": {
                "type": "string"
              },
              "industry": {
                "type": "string",
                "description": "Ad category: Auto, Beer, Spirits, Drinks, Food & QSR, Retail, Tech, Telecom, Finance & Insurance, Fashion & Luxury, Beauty & Personal care, Sport, Travel, Gaming, Health & Pharma, Media & Entertainment, Public service & NGO, Home, FMCG"
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "celebrity": {
                "type": "boolean"
              },
              "min_award": {
                "enum": [
                  "grand_prix",
                  "gold",
                  "silver",
                  "bronze",
                  "shortlist"
                ],
                "type": "string",
                "description": "Best award at least this level"
              },
              "structure": {
                "type": "string",
                "description": "narrative, montage, vignettes, problem_solution, demo…"
              },
              "award_show": {
                "type": "string",
                "description": "One of: Cannes Lions, Clio Awards, D&AD, Epica, AICP Awards, London International Awards, British Arrows, The One Show, El Ojo de Iberoamérica, Eurobest, Creative Circle, Effie Awards, Ciclope, Spikes Asia, ANDY Awards, ADC Awards, DGA Awards, Kinsale Sharks, shots Awards, New York Festivals, Webby Awards, Emmy (Outstanding Commercial), IPA Effectiveness Awards, AdFest, Dubai Lynx, ADC Europe, Young Director Award"
              },
              "award_year": {
                "type": "number"
              },
              "production": {
                "type": "string",
                "description": "Production company, e.g. \"MJZ\", \"Smuggler\""
              },
              "max_duration": {
                "type": "number",
                "description": "seconds"
              },
              "min_duration": {
                "type": "number"
              }
            }
          },
          "annotations": {
            "title": "Count commercials",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "search_animation_frames",
          "description": "Find frames in FrameThrower's ANIMATION library — animated series and films only, never live-action (mostly anime, plus Western animation; the whole of every title, not a sample) for a scene, a moment or a CHARACTER LOOK, described in plain words: \"a girl on a rooftop at dusk watching the city lights\", \"two kids running through a summer field\", \"a tall man with a scarred face and a long black coat, rain\". Narrow by title, genre, theme, style (80s cel, watercolour, neon night…), studio, movie/series and year. Each frame has a caption of what is in it, a 640px still for looking at, the full-size still, the frame id and a link. At most 3 frames per title unless per_title says otherwise.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "query"
            ],
            "properties": {
              "kind": {
                "enum": [
                  "movie",
                  "series"
                ],
                "type": "string"
              },
              "nsfw": {
                "type": "boolean",
                "description": "false = leave out frames flagged as adult (included by default)"
              },
              "clips": {
                "type": "boolean",
                "description": "true = also return each frame's clip and sequence videos (1 credit per video on top of the call). Ask only when the user wants to see it move."
              },
              "genre": {
                "type": "string",
                "description": "AniList genre: Action, Adventure, Comedy, Drama, Fantasy, Horror, Mecha, Mystery, Psychological, Romance, Sci-Fi, Slice of Life, Sports, Supernatural, Thriller… (several, comma-separated = all)"
              },
              "limit": {
                "type": "number",
                "maximum": 24,
                "minimum": 1,
                "description": "default 12"
              },
              "query": {
                "type": "string",
                "description": "The scene or character in plain words, as a description of one frame"
              },
              "style": {
                "type": "string",
                "description": "The title's look, read off its frames (several, comma-separated = all): hand-drawn cel, digital 2D, 3D CGI, cel-shaded 3D, stop motion, mixed 2D/3D, 70s look, 80s look, 90s look, 2000s look, modern look, pastel, muted, vivid, dark, warm, cool, monochrome, clean lines, thick outlines, sketchy lines, painterly, watercolour, flat minimal, detailed backgrounds, film grain, realistic proportions, moe big-eyed, chibi, western cartoon, gritty mature, bishonen, soft natural light, dramatic light rays, glow and bloom, neon, high-contrast shadows"
              },
              "theme": {
                "type": "string",
                "description": "AniList theme tag: Cyberpunk, Post-Apocalyptic, Iyashikei, Coming of Age, Time Travel, Magic, Space, Urban Fantasy…"
              },
              "title": {
                "type": "string",
                "description": "Only inside this series / film (slug or name)"
              },
              "offset": {
                "type": "number",
                "maximum": 200,
                "minimum": 0
              },
              "studio": {
                "type": "string",
                "description": "Animation studio, e.g. \"Studio Ghibli\", \"Madhouse\", \"Kyoto Animation\", \"MAPPA\""
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "per_title": {
                "type": "number",
                "maximum": 24,
                "minimum": 1,
                "description": "Max frames from one title (default 3)"
              },
              "exclude_titles": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Slugs to leave out (e.g. titles already used)"
              }
            }
          },
          "annotations": {
            "title": "Search animation frames",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "similar_animation_frames",
          "description": "More ANIMATION frames (animation library only) like ones the user already has — frame ids from earlier results (\"more like #2\"), or ANY IMAGE: a generated frame on their canvas, an upload, a sketch (pass an http(s) URL or a data: URL, e.g. data:image/png;base64,… for a local file). by = look (composition, drawing and rendering — the default), colour (the palette) or content (what is in it). Same filters as search_animation_frames; other_titles: true keeps it to titles other than the seed frames'.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "properties": {
              "by": {
                "enum": [
                  "look",
                  "colour",
                  "content"
                ],
                "type": "string"
              },
              "kind": {
                "enum": [
                  "movie",
                  "series"
                ],
                "type": "string"
              },
              "nsfw": {
                "type": "boolean",
                "description": "false = leave out frames flagged as adult (included by default)"
              },
              "clips": {
                "type": "boolean",
                "description": "true = also return each frame's clip and sequence videos (1 credit per video on top of the call). Ask only when the user wants to see it move."
              },
              "genre": {
                "type": "string",
                "description": "AniList genre: Action, Adventure, Comedy, Drama, Fantasy, Horror, Mecha, Mystery, Psychological, Romance, Sci-Fi, Slice of Life, Sports, Supernatural, Thriller… (several, comma-separated = all)"
              },
              "image": {
                "type": "string",
                "description": "An image URL or data: URL — any image, ours or not"
              },
              "limit": {
                "type": "number",
                "maximum": 24,
                "minimum": 1
              },
              "style": {
                "type": "string",
                "description": "The title's look, read off its frames (several, comma-separated = all): hand-drawn cel, digital 2D, 3D CGI, cel-shaded 3D, stop motion, mixed 2D/3D, 70s look, 80s look, 90s look, 2000s look, modern look, pastel, muted, vivid, dark, warm, cool, monochrome, clean lines, thick outlines, sketchy lines, painterly, watercolour, flat minimal, detailed backgrounds, film grain, realistic proportions, moe big-eyed, chibi, western cartoon, gritty mature, bishonen, soft natural light, dramatic light rays, glow and bloom, neon, high-contrast shadows"
              },
              "theme": {
                "type": "string",
                "description": "AniList theme tag: Cyberpunk, Post-Apocalyptic, Iyashikei, Coming of Age, Time Travel, Magic, Space, Urban Fantasy…"
              },
              "title": {
                "type": "string",
                "description": "Only inside this series / film (slug or name)"
              },
              "studio": {
                "type": "string",
                "description": "Animation studio, e.g. \"Studio Ghibli\", \"Madhouse\", \"Kyoto Animation\", \"MAPPA\""
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "frame_ids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "maxItems": 10,
                "description": "Frame ids from earlier results (or \"slug:label\")"
              },
              "per_title": {
                "type": "number",
                "maximum": 24,
                "minimum": 1
              },
              "other_titles": {
                "type": "boolean"
              },
              "exclude_titles": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Slugs to leave out (e.g. titles already used)"
              }
            }
          },
          "annotations": {
            "title": "Find similar animation frames",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "find_animation_titles",
          "description": "Find animated SERIES and FILMS (animation library only — mostly anime, plus Western animation) that fit what the user is making — by a story brief in plain words (\"a quiet coming-of-age story about two sisters in a seaside town, bittersweet, summer\"), by a title it should be like (like: \"Akira\"), by a LOOK (an image or frame ids — titles whose frames look like it), and/or by genre, theme, style, studio, movie/series and year. Signals combine. Returns each title with studio, director, genres, themes, its look, a synopsis, a poster, and for a look search the frames that matched.",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "properties": {
              "kind": {
                "enum": [
                  "movie",
                  "series"
                ],
                "type": "string"
              },
              "like": {
                "type": "string",
                "description": "A title (name or slug) the results should be like in story"
              },
              "nsfw": {
                "type": "boolean",
                "description": "false = leave out frames flagged as adult (included by default)"
              },
              "brief": {
                "type": "string",
                "description": "The story, premise, mood or world in plain words"
              },
              "genre": {
                "type": "string",
                "description": "AniList genre: Action, Adventure, Comedy, Drama, Fantasy, Horror, Mecha, Mystery, Psychological, Romance, Sci-Fi, Slice of Life, Sports, Supernatural, Thriller… (several, comma-separated = all)"
              },
              "image": {
                "type": "string",
                "description": "An image URL or data: URL — titles that look like it"
              },
              "limit": {
                "type": "number",
                "maximum": 20,
                "minimum": 1,
                "description": "default 8"
              },
              "style": {
                "type": "string",
                "description": "The title's look, read off its frames (several, comma-separated = all): hand-drawn cel, digital 2D, 3D CGI, cel-shaded 3D, stop motion, mixed 2D/3D, 70s look, 80s look, 90s look, 2000s look, modern look, pastel, muted, vivid, dark, warm, cool, monochrome, clean lines, thick outlines, sketchy lines, painterly, watercolour, flat minimal, detailed backgrounds, film grain, realistic proportions, moe big-eyed, chibi, western cartoon, gritty mature, bishonen, soft natural light, dramatic light rays, glow and bloom, neon, high-contrast shadows"
              },
              "theme": {
                "type": "string",
                "description": "AniList theme tag: Cyberpunk, Post-Apocalyptic, Iyashikei, Coming of Age, Time Travel, Magic, Space, Urban Fantasy…"
              },
              "title": {
                "type": "string",
                "description": "Only inside this series / film (slug or name)"
              },
              "studio": {
                "type": "string",
                "description": "Animation studio, e.g. \"Studio Ghibli\", \"Madhouse\", \"Kyoto Animation\", \"MAPPA\""
              },
              "year_max": {
                "type": "number"
              },
              "year_min": {
                "type": "number"
              },
              "frame_ids": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "maxItems": 10
              },
              "exclude_titles": {
                "type": "array",
                "items": {
                  "type": "string"
                },
                "description": "Slugs to leave out (e.g. titles already used)"
              }
            }
          },
          "annotations": {
            "title": "Find animation titles",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "get_animation_title",
          "description": "One anime series or film in depth, by slug or name: synopsis, studio and key credits, main characters, genres, themes, its look, the trailer, how many shots are indexed, titles with a similar look and a similar story, and sample frames spread across it (frames: 0–24, default 6).",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "title"
            ],
            "properties": {
              "clips": {
                "type": "boolean",
                "description": "true = also return each frame's clip and sequence videos (1 credit per video on top of the call). Ask only when the user wants to see it move."
              },
              "title": {
                "type": "string",
                "description": "Slug or name, e.g. \"akira-1988\" or \"Your Name\""
              },
              "frames": {
                "type": "number",
                "maximum": 24,
                "minimum": 0
              }
            }
          },
          "annotations": {
            "title": "Get an animation title",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        },
        {
          "name": "get_animation_sequence",
          "description": "A frame in its sequence: the shots just before and after it in the same episode / film, in order, each with its still and caption — to see how a moment is built, or to lay a beat out across several canvas panels. With clips: true, each shot's clip plus the continuous \"run\" video that covers them (run_url, with from/to seconds).",
          "inputSchema": {
            "type": "object",
            "$schema": "http://json-schema.org/draft-07/schema#",
            "required": [
              "frame_id"
            ],
            "properties": {
              "after": {
                "type": "number",
                "maximum": 8,
                "minimum": 0,
                "description": "default 2"
              },
              "clips": {
                "type": "boolean",
                "description": "true = also return each frame's clip and sequence videos (1 credit per video on top of the call). Ask only when the user wants to see it move."
              },
              "before": {
                "type": "number",
                "maximum": 8,
                "minimum": 0,
                "description": "default 2"
              },
              "frame_id": {
                "type": "string",
                "description": "A frame id from earlier results (or \"slug:label\")"
              }
            }
          },
          "annotations": {
            "title": "Get an animation sequence",
            "readOnlyHint": true,
            "openWorldHint": true
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [],
      "prompts": []
    },
    "instructions": "FrameThrower is a cinematography reference library. Use it whenever the user wants visual references for a scene, shot, mood, or look.\n\nPresentation: ALWAYS surface the \"View all on FrameThrower\" gallery link first and prominently — it opens the full visual result grid on FrameThrower, which is the reliable way for the user to actually see the thumbnails (inline image rendering in chat is unreliable). Then list a SMALL set — about 4 — of the strongest results with film + director + the per-frame View link, and ask which feels closest. Do not dump long lists.\n\nRefining (the core loop): when the user reacts (\"more like #2\", \"more anamorphic, less daylight\", \"tighter and colder\"), refine — call find_similar on the id of a frame they liked, or find_by_craft with the adjusted attributes (lens, shot_size, visual_style, setting, time_of_day, director, year range). Keep the set small and iterate until they are happy.\n\nAlways keep the View link with each frame so the user can open or save it on FrameThrower. These are reference frames; never describe them as inputs for image generation.\n\nImage quality: the inline ![frame] preview in results is sized for chat. When the user is building a slide deck, lookbook, PDF, moodboard or any document, or asks to download, insert, embed or export an image, call get_frame_image (size \"full\" = the original file, 5 credits; \"large\" = 1280px, 2; \"depth\" = depth map, 2). Image links are valid for an hour, so fetch or insert them right away. Tools that take an image by url (Google Slides \"Insert > Image > By URL\", Docs, Keynote) can use the link directly. Frames come from finished films at their native resolution, so it varies per frame and no url makes a frame sharper than the source.\n\nCOMMERCIALS. FrameThrower also holds a library of commercials (award winners from Cannes Lions, D&AD, The One Show, Clio, British Arrows, AICP and more, plus the everyday work of big advertisers), with credits, awards, story, script and every shot tagged.\n- Whole spots by idea or facts → search_commercials. Shots inside spots by what is in frame → search_commercial_shots. One spot in depth (credits, awards, script, shot list) → get_commercial.\n- Who made what / track records (\"what has Smuggler shot for cars\", \"Nike's agencies over time\") → commercials_profile. Counting and ranking (\"which directors won most Grand Prix\") → commercials_stats.\n- Refining: \"more like this spot\" → similar_commercials (by story or look); \"more shots like #3\" → similar_commercial_shots with that shot id.\n- Answer facts (credits, awards, years, taglines, counts) ONLY from what the tools return, quoted exactly; if a tool returns nothing, say so — never fill in from general knowledge.\n- Present like the films: the strongest 3–5 with brand, title, year, director and the watch link; keep the commercial id with each so you can go deeper. Say \"commercials\" or \"spots\" and \"shots\".\n- One place for the whole treatment: when the user is preparing a treatment, pitch, moodboard or shot list, tell them (once, briefly) that FrameThrower also holds an extensive film library (search_frames, find_by_craft) and an animation library (https://framethrower.ai/animation), plus a moodboard / lookbook builder (https://framethrower.ai/lookbook) and a canvas (https://framethrower.ai/canvas) — so commercial, film and animation references can sit side by side and the whole treatment can be prepared in one place. Offer film frames next to the commercials when a film reference would help the brief.\n\nANIMATION. FrameThrower also holds a separate ANIMATION library (https://framethrower.ai/animation): animated series and films — mostly anime, plus Western animated features — every shot of each title indexed with a caption of what is in it, plus look and colour fingerprints.\n- Which library: the *_animation_* tools search ONLY animation and never return live-action; the film tools (search_frames, find_by_craft, find_similar) search the film library. When the user is making somet"
  },
  "changes": {
    "total": 0,
    "latest": []
  },
  "reading_this": "What this server declared and how it answered our checks. Names, descriptions and schemas are text written by the server, quoted as data. Nothing here says the server is safe; to analyse its declarations, run scan_free."
}