{
  "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": "catalystproject.ai",
    "site": "catalystproject.ai",
    "addresses": [
      {
        "address": "216.198.79.1",
        "endpoints": 712,
        "shared_infrastructure": true,
        "network": {
          "asn": 16509,
          "name": "AMAZON-02 - Amazon.com, Inc.",
          "prefix": "216.198.79.0/24",
          "country": "US"
        }
      }
    ],
    "addresses_recorded": true,
    "address_history": [
      {
        "addresses": [
          "216.198.79.1"
        ],
        "first_seen": "2026-11-22T04:42:01.455Z",
        "last_seen": "2026-11-22T04:42:01.455Z",
        "checks": 1
      }
    ],
    "hosting": [
      {
        "value": "Vercel",
        "evidence": "Server header \"Vercel\""
      }
    ],
    "software": [],
    "server_info": {
      "name": "catalyst-evidence-graph",
      "version": "0.2.0",
      "protocol_version": "2025-06-18"
    },
    "headers": {
      "server": "Vercel",
      "strict-transport-security": "max-age=63072000"
    },
    "auth": null
  },
  "related": {
    "same_address": {
      "total": 711,
      "sample": [
        {
          "id": "6",
          "url": "https://ase.academy/mcp",
          "server_name": "academy.ase/periodic-system",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:31:06.407Z"
        },
        {
          "id": "24",
          "url": "https://genosys.ae/mcp",
          "server_name": "ae.genosys/genosys",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:31:08.432Z"
        },
        {
          "id": "54",
          "url": "https://state.1court.ai/api/mcp",
          "server_name": "ai.1court.state/court-directory",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:33:01.582Z"
        },
        {
          "id": "85",
          "url": "https://aeoengine.ai/mcp",
          "server_name": "ai.aeoengine/best-ai-search-agency-aeo-report",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:33:01.583Z"
        },
        {
          "id": "164",
          "url": "https://agentmash.ai/mcp",
          "server_name": "ai.agentmash/agentmash",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:33:02.249Z"
        },
        {
          "id": "170",
          "url": "https://agentsrank.ai/api/mcp",
          "server_name": "ai.agentsrank/agentsrank",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:33:02.367Z"
        },
        {
          "id": "263",
          "url": "https://artidrop.ai/mcp",
          "server_name": "ai.artidrop/artidrop",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:37:01.251Z"
        },
        {
          "id": "406",
          "url": "https://boltclaw.ai/docs/mcp-server",
          "server_name": "ai.boltclaw/docs",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:41:01.611Z"
        },
        {
          "id": "484",
          "url": "https://centralcity.ai/mcp/open",
          "server_name": "ai.centralcity/central-city",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:42:01.700Z"
        },
        {
          "id": "487",
          "url": "https://certifikit.ai/mcp",
          "server_name": "ai.certifikit/coi-tools",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:42:01.454Z"
        },
        {
          "id": "767",
          "url": "https://emergenttechnologies.ai/mcp",
          "server_name": "ai.emergenttechnologies/emergent",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:49:00.812Z"
        },
        {
          "id": "1206",
          "url": "https://ihumane.ai/mcp",
          "server_name": "ai.ihumane/ihumane",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:57:01.453Z"
        },
        {
          "id": "1245",
          "url": "https://www.iolee.ai/mcp",
          "server_name": "ai.iolee/hotel-info",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:58:01.338Z"
        },
        {
          "id": "1256",
          "url": "https://jawz.ai/api/mcp",
          "server_name": "ai.jawz/jawz",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T04:59:01.357Z"
        },
        {
          "id": "1403",
          "url": "https://lifescenario.ai/api/mcp",
          "server_name": "ai.lifescenario/info",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T05:02:01.707Z"
        },
        {
          "id": "2450",
          "url": "https://stackrate.ai/mcp",
          "server_name": "ai.stackrate/comparisons",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:50:04.100Z"
        },
        {
          "id": "2467",
          "url": "https://stimhaus.ai/mcp",
          "server_name": "ai.stimhaus/emma-for-agents",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:50:04.598Z"
        },
        {
          "id": "2543",
          "url": "https://tazilo.ai/mcp",
          "server_name": "ai.tazilo/profiles",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:51:09.864Z"
        },
        {
          "id": "2885",
          "url": "https://whichagent.ai/api/categories/beauty/mcp",
          "server_name": "ai.whichagent/beauty",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:54:03.019Z"
        },
        {
          "id": "2886",
          "url": "https://whichagent.ai/api/categories/car-rental/mcp",
          "server_name": "ai.whichagent/car-rental",
          "last_state": "listed",
          "last_checked_at": "2026-11-22T06:55:02.240Z"
        }
      ]
    },
    "same_site": {
      "total": 0,
      "sample": []
    },
    "same_tool_list": {
      "total": 0,
      "sample": []
    },
    "same_publisher": {
      "publisher": "ai.catalystproject",
      "total": 0,
      "sample": []
    },
    "same_repository": {
      "repository_url": "https://github.com/colorcatalyst/catalyst-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": "474",
    "server_name": "ai.catalystproject/evidence-graph",
    "url": "https://catalystproject.ai/mcp",
    "host": "catalystproject.ai",
    "transport": "streamable-http",
    "last_checked_at": "2026-11-22T04:42:01.455Z",
    "last_state": "listed",
    "last_detail": null,
    "consecutive_failures": 0,
    "current_sha": "a45c8c70e3f8f41e3c41df22cbffc167d0894a404311c60b585c941401b2183f",
    "first_listed_at": "2026-11-21T04:41:01.496Z",
    "created_at": "2026-11-21T04:30:12.572Z",
    "resolved_addresses": [
      "216.198.79.1"
    ]
  },
  "server": {
    "name": "ai.catalystproject/evidence-graph",
    "title": "Catalyst evidence graph",
    "description": "Findings on what compounds and supplements do in the body, with evidence strength, quote and paper.",
    "version": "0.2.0",
    "registry_status": "active",
    "repository_url": "https://github.com/colorcatalyst/catalyst-mcp",
    "website_url": "https://catalystproject.ai/connect",
    "published_at": "2026-10-04T20:43:24.132Z",
    "updated_at": "2026-10-04T20:43:24.132Z",
    "first_seen": "2026-11-21T04:30:11.935Z"
  },
  "other_endpoints": [],
  "intel": {
    "capabilities": [],
    "evm_addresses": [],
    "chains": [],
    "tokens": [],
    "computed_at": "2026-11-22T14:51:06.422Z"
  },
  "needs_sign_in": false,
  "reachability": {
    "window_days": 30,
    "checks": 2,
    "answered": 2,
    "answered_percent": 100,
    "avg_listing_latency_ms": 597,
    "first_check_in_window": "2026-11-21T04:41:01.496Z",
    "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": "a45c8c70e3f8f41e3c41df22cbffc167d0894a404311c60b585c941401b2183f",
    "tools": 7,
    "resources": 2,
    "prompts": 1,
    "first_seen": "2026-11-21T04:41:02.135Z",
    "tool_names": [
      "find_evidence",
      "search_nodes",
      "get_findings",
      "get_finding",
      "get_relations",
      "get_reactions",
      "reach"
    ],
    "declared": {
      "tools": [
        {
          "name": "find_evidence",
          "title": "Find the evidence on a substance or a question",
          "description": "Answers \"what does X do?\" and \"does X affect Y?\" for a supplement, nutrient, drug, food compound or plant (for example \"does magnesium help sleep?\", \"what is creatine shown to do?\", \"omega-3 and triglycerides\"). Pass the substance as query and the effect or outcome asked about, if there is one, as about. When the person names two substances (\"is creatine safe with caffeine\"), pass one as query and the other as about, in one call; findings about the pair together come back under in_combination. It resolves the name to the node that has findings and returns up to limit findings (default 10), strongest evidence first, each with its evidence strength in words, the study design, the quote, the paper, a permalink and a citation to quote as it stands. total_findings counts every reported finding that matches; hypotheses counts the inferred rows listed beside them. The result is complete for the query: another wording of the same substance resolves to the same node, so do not call again to rephrase. Call again only to narrow (evidence_strength, about), to raise limit (at most 50), or to ask about something else. Without about, summary lists everything the node has findings about. If matched is null, or total_findings is 0, Catalyst has recorded no findings on it. That is a complete answer: say so, and do not answer from memory as though from Catalyst. Try search_nodes only when other_matches or summary shows a node the person plausibly meant. An evidence strength says how well the evidence supports a finding and is not a recommendation. For what a compound can become, use reach; for reference-database relations, use get_relations.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "query"
            ],
            "properties": {
              "about": {
                "type": "string",
                "maxLength": 80,
                "minLength": 2,
                "description": "Optional: the effect, outcome or second substance asked about (e.g. \"sleep\", \"blood pressure\", \"caffeine\"), or a node id from search_nodes."
              },
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 50,
                "minimum": 1,
                "description": "Findings to return, strongest evidence first. The default is enough to answer; total_findings says how many match."
              },
              "query": {
                "type": "string",
                "maxLength": 80,
                "minLength": 2,
                "description": "The substance the person asked about, in their words (e.g. \"magnesium\", \"vitamin D\", \"BPC-157\"), or a node id from search_nodes. For a question about an outcome alone (e.g. \"what lowers blood pressure\"), the outcome."
              },
              "detail": {
                "enum": [
                  "brief",
                  "full"
                ],
                "type": "string",
                "default": "brief",
                "description": "brief (default) returns each finding with its claim, evidence strength, design, population, dose, quote, paper, permalink and a citation to quote as it stands. full adds every other recorded field and is longer; use it only when the person asks for all fields."
              },
              "evidence_strength": {
                "enum": [
                  "strong",
                  "moderate",
                  "limited",
                  "very_limited",
                  "insufficient"
                ],
                "type": "string",
                "description": "Optional floor: only findings at this evidence strength or stronger, from strong down to insufficient."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "Find the evidence on a substance or a question",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "search_nodes",
          "title": "Find a compound, outcome or protein",
          "description": "Looks up the node id for a compound, protein, organism or outcome by name or synonym (for example \"CoQ10\", \"caffeine\", \"CYP1A2\", \"sleep\"). Use it to get the id that get_findings, get_finding, get_relations, get_reactions and reach take; for a question about what a substance does, call find_evidence instead, which needs no id. Returns up to 10 hits, each with id, label, type and the number of findings; hits with findings come first, so the first hit with findings above 0 is usually the one to use. An enzyme or transporter has type protein. It says nothing about a node beyond its id and how many findings it has. If with_findings is 0 the graph holds no findings for the name; the hits may still be the right node for get_relations, get_reactions or reach.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "query"
            ],
            "properties": {
              "query": {
                "type": "string",
                "maxLength": 80,
                "minLength": 2,
                "description": "A name, synonym or short phrase, e.g. \"CoQ10\" or \"vitamin D\". One substance per call."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "Find a compound, outcome or protein",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_findings",
          "title": "Findings about a node, with their evidence strength",
          "description": "Lists the curated study findings for one node by id, from search_nodes: for a compound, organism or material, what it has been shown to affect; for an outcome, which compounds have been studied against it. Use it to browse a node by id. For a question in words, such as \"does X help Y\", find_evidence answers in one call and needs no id. summary has one row per thing the node has findings about, counted over all its findings and not only the rows returned. The default number of findings, strongest first, is enough to answer. There is no offset: to see a different slice, pass about (an id from summary, or words such as \"sleep\") or evidence_strength. Each finding carries its evidence strength, one of five named levels from strong to insufficient (strong, moderate, limited, very_limited, insufficient), the verbatim sentence it was drawn from, the paper, the population and dose, and a permalink. An evidence strength says how well the evidence supports the finding and is not a recommendation; give it with the claim, and link the permalink. An empty list means no findings are recorded for that node, a complete answer that does not show the compound does nothing; empty_means says why.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "node_id"
            ],
            "properties": {
              "about": {
                "type": "string",
                "maxLength": 80,
                "minLength": 2,
                "description": "Optional: only findings about this, as an id from summary (e.g. CAT:outcome/sleep-onset-latency) or words in its name (e.g. \"sleep\")."
              },
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 50,
                "minimum": 1,
                "description": "Findings to return, strongest evidence first (1 to 50). The default is enough to answer."
              },
              "detail": {
                "enum": [
                  "brief",
                  "full"
                ],
                "type": "string",
                "default": "brief",
                "description": "brief (default) returns each finding with its claim, evidence strength, design, population, dose, quote, paper, permalink and a citation to quote as it stands. full adds every other recorded field and is longer; use it only when the person asks for all fields."
              },
              "node_id": {
                "type": "string",
                "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
                "maxLength": 120,
                "minLength": 3,
                "description": "A node id in the form PREFIX:local, e.g. CHEBI:16919 (creatine). Get it from the id field of a search_nodes hit."
              },
              "evidence_strength": {
                "enum": [
                  "strong",
                  "moderate",
                  "limited",
                  "very_limited",
                  "insufficient"
                ],
                "type": "string",
                "description": "Optional floor: only findings at this evidence strength or stronger, from strong down to insufficient."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "Findings about a node, with their evidence strength",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_finding",
          "title": "One finding, with its evidence strength explained",
          "description": "Explains one finding by its finding id: the claim, its evidence strength and what that level means, the verbatim quote, the study design and the paper, and evidence_strength_reasons, each rule that set the level in order, and what the assessment does not weigh. The finding id is 26 characters, from the id field of a find_evidence or get_findings finding, or the last part of its permalink (/e/{id}). Use it to answer why the evidence behind a finding is as strong as it is, from evidence_strength_reasons and never by guessing. To find findings, use find_evidence or get_findings; this tool takes no name. A head-to-head comparison id returns a sentence naming the page that shows the comparison, not a finding.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "finding_id"
            ],
            "properties": {
              "finding_id": {
                "type": "string",
                "pattern": "^[0-9A-HJKMNP-TV-Z]{26}$",
                "description": "A 26-character finding id: the id of a finding from find_evidence or get_findings, or the last part of its permalink."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "One finding, with its evidence strength explained",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_relations",
          "title": "Reference-database relations (hypotheses)",
          "description": "Lists what public reference databases (Reactome, UniProt, Rhea, ChEBI and others) record about one node by id, from search_nodes: transporters, enzymes, pathways, expression. Every row is assertion_class 'inferred': a hypothesis about how a compound could act, not a result anyone measured in people. Present these as possible mechanisms and never as effects. For effects, use find_evidence. For the reactions a compound or enzyme takes part in, use get_reactions; for what a compound can become, use reach. predicate limits the list to one relation type, named as in the predicate field of a row (for example transported_by for transporters, metabolized_by for enzymes). Returns total and up to limit rows (default 10); offset pages the rest, and the default is enough to answer. A page too large for one result is cut to fit, and truncated with next_offset says how to get the rest. An empty list with a predicate means the databases record no relation of that type for this node. That is a complete answer, so do not repeat the call with the same predicate. Leave predicate out once only when the person asked broadly and you need to see which types the node has.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "node_id"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 50,
                "minimum": 1,
                "description": "Rows to return (1 to 50)."
              },
              "offset": {
                "type": "integer",
                "default": 0,
                "maximum": 10000,
                "minimum": 0,
                "description": "Rows to skip, to page past limit."
              },
              "node_id": {
                "type": "string",
                "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
                "maxLength": 120,
                "minLength": 3,
                "description": "A node id in the form PREFIX:local, e.g. CHEBI:16919 (creatine). Get it from the id field of a search_nodes hit."
              },
              "predicate": {
                "enum": [
                  "transported_by",
                  "substrate_of",
                  "inhibits",
                  "activates",
                  "binds",
                  "metabolized_by",
                  "converted_to",
                  "participates_in",
                  "regulates",
                  "expressed_in",
                  "absorbed_at",
                  "accumulates_in",
                  "affects",
                  "depletes",
                  "requires_cofactor",
                  "contraindicated_with",
                  "alters_exposure_of",
                  "contradicts",
                  "has_adi",
                  "response_varies_by",
                  "has_functional_parent",
                  "enantiomer_of",
                  "has_hepatotoxicity_likelihood",
                  "regulates_expression_of",
                  "interacts_with",
                  "covaries_with",
                  "affects_phenotype",
                  "has_phenotype",
                  "has_germline_basis_in",
                  "located_in",
                  "part_of",
                  "affects_relative_to"
                ],
                "type": "string",
                "description": "Limit to one relation type, as in the predicate field of a row, e.g. transported_by."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "Reference-database relations (hypotheses)",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "get_reactions",
          "title": "Reactions a compound or protein takes part in (inferred)",
          "description": "Lists the biochemical reactions from Rhea and Human-GEM that a compound is a substrate or product of, or that a protein (enzyme) catalyses or transports, by node id from search_nodes. It lists reactions and does not answer a route question: for \"can X become Y\" or \"what can X become\", use reach. Every row is assertion_class 'inferred': a reaction two public databases record, not a result anyone measured in a person. Present these as known biochemistry, never as an effect a compound has, and never as a recommendation. For effects, use find_evidence. Returns total and up to limit reactions (default 10), each with its equation, its participants by side, id and label, the first five enzymes with catalyst_count for all of them, and its source; offset pages the rest, and the default is enough to answer. A page too large for one result is cut to fit, and truncated with next_offset says how to get the rest. A compound flagged is_hub (water, ATP, protons and the like) returns its reaction count only, because it takes part in nearly every reaction. Coverage is one Rhea release and one Human-GEM release; a participant that is not a node in this graph is listed with a null id, and only human enzymes that are nodes are listed. An empty result means no reaction in those releases names this node. That is a complete answer and does not show the body has none.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "node_id"
            ],
            "properties": {
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 50,
                "minimum": 1,
                "description": "Reactions to return (1 to 50). Each carries its participants and enzymes; the default is enough to answer."
              },
              "offset": {
                "type": "integer",
                "default": 0,
                "maximum": 10000,
                "minimum": 0,
                "description": "Reactions to skip, to page past limit."
              },
              "node_id": {
                "type": "string",
                "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
                "maxLength": 120,
                "minLength": 3,
                "description": "A node id in the form PREFIX:local, e.g. CHEBI:16919 (creatine). Get it from the id field of a search_nodes hit."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "Reactions a compound or protein takes part in (inferred)",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        },
        {
          "name": "reach",
          "title": "What a compound can become, and through what (inferred, a hypothesis)",
          "description": "Answers a route question: \"can X become Y in the body\" (give from_id and to_id) and \"what can X become\" (give only from_id). Both ids are compound node ids from search_nodes, so a question that names two compounds needs one search_nodes call for each first. It searches the reactions two public databases (Rhea, Human-GEM) record, up to depth steps (1 to 3, default 3), and returns the routes with the reactions and enzymes along each. Every route is assertion_class 'inferred': a hypothesis drawn from reference databases, never a measured or reported effect. Present it as known biochemical connectivity, never as an effect, a recommendation, or a claim that the body actually does this. For measured effects, use find_evidence. Common cofactors and currency species (water, ATP, protons and the like) are not used as intermediate steps, so a route never reads 'reaches everything through ATP'. A currency species given as from_id or to_id returns reachable: null with a coverage note, not a checked 0 routes. With from_id alone it lists up to limit routes (default 10, offset pages the rest); a page too large for one result is cut to fit, and truncated with next_offset says how to get the rest. When no route is found, the coverage field says which of three cases it is: reachability has not been built for this scope yet, so nothing was checked; it was checked and no route exists through the reactions loaded, which does not mean the body cannot make it; or the compound is a currency species and was never searched. The answer is in that one result; another tool does not check it again.",
          "inputSchema": {
            "type": "object",
            "$schema": "https://json-schema.org/draft/2020-12/schema",
            "required": [
              "from_id"
            ],
            "properties": {
              "depth": {
                "type": "integer",
                "default": 3,
                "maximum": 3,
                "minimum": 1,
                "description": "Longest route to consider, in reaction steps (1 to 3)."
              },
              "limit": {
                "type": "integer",
                "default": 10,
                "maximum": 50,
                "minimum": 1,
                "description": "Routes to return when to_id is omitted (1 to 50)."
              },
              "to_id": {
                "type": "string",
                "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
                "maxLength": 120,
                "minLength": 3,
                "description": "A target compound: a compound node id from search_nodes. Omit to list everything from_id reaches."
              },
              "offset": {
                "type": "integer",
                "default": 0,
                "maximum": 10000,
                "minimum": 0,
                "description": "Routes to skip when to_id is omitted, to page past limit."
              },
              "from_id": {
                "type": "string",
                "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
                "maxLength": 120,
                "minLength": 3,
                "description": "The compound to start from: a compound node id from search_nodes."
              }
            },
            "additionalProperties": {}
          },
          "annotations": {
            "title": "What a compound can become, and through what (inferred, a hypothesis)",
            "readOnlyHint": true,
            "openWorldHint": false,
            "idempotentHint": true,
            "destructiveHint": false
          }
        }
      ],
      "tools_omitted": 0,
      "resources": [
        {
          "name": "evidence-card",
          "uri": "ui://catalyst/evidence-card.html",
          "mimeType": "text/html;profile=mcp-app",
          "description": "Draws find_evidence results with the strength of each finding."
        },
        {
          "name": "guide",
          "uri": "catalyst://guide",
          "mimeType": "text/markdown",
          "description": "The five levels of evidence strength and how to cite a finding."
        }
      ],
      "prompts": [
        {
          "name": "answer_with_evidence",
          "description": "Answer a question about what a substance does in the body from Catalyst, giving the strength of the evidence for every claim.",
          "arguments": [
            {
              "name": "question",
              "required": true,
              "description": "The question, e.g. \"Does magnesium help sleep?\""
            }
          ]
        }
      ]
    },
    "instructions": "Catalyst is building computational infrastructure for human biology, starting with a provenance-aware knowledge graph of biological entities and biomedical findings. The current MCP interface exposes graph search, study findings with their evidence strength, and biological relationships; a research engine and physiological simulation are roadmap capabilities. All seven tools only read; nothing is written, sent or bought. For what a substance does, or whether it affects something, call find_evidence once: it resolves the name and returns the findings, strongest first, and that one result is the whole answer for the query. Use search_nodes to get a node id for the other tools, get_findings to list one node's findings, get_finding to explain one finding, get_relations and get_reactions for what reference databases record, and reach for whether or what a compound can become. Every evidence strength here is computed from the study behind it (design, population, replication), never written by hand. It is one of five named levels: strong, moderate, limited, very_limited, insufficient. An evidence strength describes how well the evidence supports a finding. It is not a recommendation to take anything, and it is not medical advice. Present each finding with its evidence strength in words, and link its permalink so the reader can check the quote and the paper. A row whose assertion_class is 'inferred' is a hypothesis drawn from a reference database, not a reported result: call it a hypothesis. Do not merge findings into a stronger claim than the strongest evidence supports, and say so when findings contradict each other."
  },
  "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."
}