Catalyst evidence graph

Official7 tools

by colorcatalyst · JavaScript

Findings on what compounds and supplements do in the body, with evidence strength, quote and paper.

ai.catalystproject/evidence-graph MCP Server

The ai.catalystproject/evidence-graph MCP server provides findings on what compounds and supplements do in the body. Results include evidence strength, a quote, and a paper reference, based on the server’s description.

🛠️ Key Features

Findings focused on compounds and supplements
Evidence strength included with results
Provides a quote
Includes a paper reference

🚀 Use Cases

Reviewing how specific compounds or supplements act in the body
Comparing varying levels of evidence across papers

⚡ Developer Benefits

Structured outputs centered on evidence strength
Direct access to quoted text and cited papers

⚠️ Limitations

Scope is limited to “compounds and supplements” and their effects “in the body,” as described

Topics

biochemistryclaude-code-pluginevidence-based-medicinegemini-cli-extensionknowledge-graphmcpmcp-servermodel-context-protocolnutritionsupplementsvscode-extension

Captured live from the server via tools/list.

find_evidence

Use this when someone asks what a supplement, nutrient, drug, food compound or plant does in the body, or whether it affects something specific (for example "does magnesium help sleep?", "what is creatine shown to do?", "omega-3 and triglycerides"). Pass the substance (or an outcome such as "sleep") as query, and the specific effect, if there is one, as about. One call resolves the name to the node that has findings and returns them, each with its evidence strength in words, the study design, the quote, the paper, a permalink and a citation to quote as it stands. Without about, summary lists everything the node has findings about. If nothing matches, it says so: tell the person Catalyst has no findings on it rather than answering from memory as though from Catalyst. An evidence strength says how well the evidence supports a finding; it is not a recommendation.

Parameters5

query	string	required	The substance or outcome the person asked about, in their words (e.g. "magnesium", "vitamin D", "sleep"), or a node id.
about	string	optional	Optional: the specific effect or outcome asked about (e.g. "sleep", "blood pressure"), or a node id.
evidence_strength	string	optional	Optional floor: only findings with at least this evidence strength.
limit	integer	optional	Findings to return, strongest evidence first.
detail	string	optional	brief (default): each finding with its claim, evidence strength, design, population, dose, quote, paper, permalink and a ready-to-quote citation. full: every recorded field.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "maxLength": 80,
      "description": "The substance or outcome the person asked about, in their words (e.g. \"magnesium\", \"vitamin D\", \"sleep\"), or a node id."
    },
    "about": {
      "description": "Optional: the specific effect or outcome asked about (e.g. \"sleep\", \"blood pressure\"), or a node id.",
      "type": "string",
      "minLength": 2,
      "maxLength": 80
    },
    "evidence_strength": {
      "description": "Optional floor: only findings with at least this evidence strength.",
      "type": "string",
      "enum": [
        "strong",
        "moderate",
        "limited",
        "very_limited",
        "insufficient"
      ]
    },
    "limit": {
      "default": 10,
      "description": "Findings to return, strongest evidence first.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "detail": {
      "default": "brief",
      "description": "brief (default): each finding with its claim, evidence strength, design, population, dose, quote, paper, permalink and a ready-to-quote citation. full: every recorded field.",
      "type": "string",
      "enum": [
        "brief",
        "full"
      ]
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

search_nodes

Search the Catalyst evidence graph by name or synonym (for example "magnesium", "vitamin D", "sleep", "creatine"). Returns node ids to pass to get_findings or get_relations. Each hit says how many findings it has, and hits with findings come first, so the first hit with findings above 0 is usually the one to use. It finds things; it does not say anything about them.

Parameters1

query

string

required

A name, synonym or phrase.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "maxLength": 80,
      "description": "A name, synonym or phrase."
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

get_findings

The curated study findings for one node: for a compound, organism or material, what it has been shown to affect; for an outcome, which compounds have been studied against it. summary lists everything the node has findings about, one row each, across ALL its findings and not only the rows returned. Use it to see what is covered, then pass about (an id from summary, or words such as "sleep") to get the findings on one thing. 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; it is not a recommendation. Always give the evidence strength with the claim, and link the permalink. An empty list means nothing has been curated yet, not that the compound does nothing.

Parameters5

node_id	string	required	A node id from search_nodes, e.g. CHEBI:16919 (creatine).
limit	integer	optional	Findings to return, strongest evidence first.
about	string	optional	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").
evidence_strength	string	optional	Optional floor: return only findings with at least this evidence strength.
detail	string	optional	brief (default): each finding with its claim, evidence strength, design, population, dose, quote, paper, permalink and a ready-to-quote citation. full: every recorded field.

Raw schema

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "minLength": 3,
      "maxLength": 120,
      "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
      "description": "A node id from search_nodes, e.g. CHEBI:16919 (creatine)."
    },
    "limit": {
      "default": 20,
      "description": "Findings to return, strongest evidence first.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "about": {
      "description": "Optional: only findings about this, as an id from summary (e.g. CAT:outcome/sleep-onset-latency) or words in its name (e.g. \"sleep\").",
      "type": "string",
      "minLength": 2,
      "maxLength": 80
    },
    "evidence_strength": {
      "description": "Optional floor: return only findings with at least this evidence strength.",
      "type": "string",
      "enum": [
        "strong",
        "moderate",
        "limited",
        "very_limited",
        "insufficient"
      ]
    },
    "detail": {
      "default": "brief",
      "description": "brief (default): each finding with its claim, evidence strength, design, population, dose, quote, paper, permalink and a ready-to-quote citation. full: every recorded field.",
      "type": "string",
      "enum": [
        "brief",
        "full"
      ]
    }
  },
  "required": [
    "node_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

get_finding

One finding by its id (the last part of a permalink, /e/{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. Use it to explain why the evidence behind a finding is as strong as it is, from evidence_strength_reasons rather than by guessing.

Parameters1

finding_id

string

required

A 26-character finding id, from a permalink or get_findings.

Raw schema

{
  "type": "object",
  "properties": {
    "finding_id": {
      "type": "string",
      "pattern": "^[0-9A-HJKMNP-TV-Z]{26}$",
      "description": "A 26-character finding id, from a permalink or get_findings."
    }
  },
  "required": [
    "finding_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

get_relations

What public reference databases (Reactome, UniProt, Rhea, ChEBI and others) record about a node: 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 get_findings.

Parameters4

node_id	string	required	A node id from search_nodes, e.g. CHEBI:16919 (creatine).
predicate	string	optional	Limit to one relation type, e.g. transports.
limit	integer	optional
offset	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "minLength": 3,
      "maxLength": 120,
      "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
      "description": "A node id from search_nodes, e.g. CHEBI:16919 (creatine)."
    },
    "predicate": {
      "description": "Limit to one relation type, e.g. transports.",
      "type": "string",
      "maxLength": 40,
      "pattern": "^[a-z_]+$"
    },
    "limit": {
      "default": 25,
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    }
  },
  "required": [
    "node_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

get_reactions

Biochemical reactions from Rhea and Human-GEM that a compound is a substrate or product of, or that a protein catalyses or transports. 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 get_findings. A compound flagged is_hub (water, ATP, protons and the like) returns its reaction count only, because it participates in nearly everything and a row list would not be biology anyone reads. Coverage: the whole of one Rhea release and one Human-GEM release, each reaction counted once; a participant that is not a node in this graph is listed but not linked, and only human enzymes that are nodes are listed at all. An empty result means no reaction in those releases names this node, not that the body has none.

Parameters3

node_id	string	required	A node id from search_nodes, e.g. CHEBI:16919 (creatine).
limit	integer	optional
offset	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "minLength": 3,
      "maxLength": 120,
      "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
      "description": "A node id from search_nodes, e.g. CHEBI:16919 (creatine)."
    },
    "limit": {
      "default": 25,
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    }
  },
  "required": [
    "node_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

reach

Breadth-first reachability through the reactions two public databases (Rhea, Human-GEM) record: what a compound could become, and through which reactions and enzymes, within up to 3 steps. 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 get_findings. Common cofactors and currency species (water, ATP, protons and the like) are excluded as intermediate steps, so a route never reads 'reaches everything through ATP'. A currency species is also never materialised as from_id or to_id itself — asking about one returns reachable: null with a coverage note explaining that, not a checked "0 routes". Give to_id to check one target compound; omit it to list everything from_id reaches. A route not being found can mean three different things, and the result's coverage field says which: reachability may not have been BUILT for this scope yet (nothing has been checked); it may have been checked and found NOT REACHABLE through the reactions loaded — never read that as "the body cannot make it"; or the compound asked about may be a currency species, structurally excluded rather than searched.

Parameters5

from_id	string	required	The compound to start from.
to_id	string	optional	A target compound. Omit to list everything from_id reaches.
depth	integer	optional	Longest route to consider, in reaction steps (1-3).
limit	integer	optional	Rows to return when to_id is omitted.
offset	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "from_id": {
      "type": "string",
      "minLength": 3,
      "maxLength": 120,
      "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$",
      "description": "The compound to start from."
    },
    "to_id": {
      "description": "A target compound. Omit to list everything from_id reaches.",
      "type": "string",
      "minLength": 3,
      "maxLength": 120,
      "pattern": "^[A-Za-z_]+:[A-Za-z0-9_./+-]+$"
    },
    "depth": {
      "default": 3,
      "description": "Longest route to consider, in reaction steps (1-3).",
      "type": "integer",
      "minimum": 1,
      "maximum": 3
    },
    "limit": {
      "default": 25,
      "description": "Rows to return when to_id is omitted.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "default": 0,
      "type": "integer",
      "minimum": 0,
      "maximum": 10000
    }
  },
  "required": [
    "from_id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": {}
}

README.md4 KBView on GitHub

Catalyst evidence graph — MCP server, plugins and extensions

Catalyst is a curated evidence graph of what compounds, supplements, nutrients and foods have been shown to do in the human body. This repository connects it to the assistants and editors people already use. The server itself is hosted; everything here only tells a client where it is.

Server: https://catalystproject.ai/mcp — MCP over Streamable HTTP, read-only, no account, no key. Registry name: ai.catalystproject/evidence-graph Setup for every client, the tool list and limits: https://catalystproject.ai/connect

What an assistant gets

Findings for a compound or an outcome. Every finding carries an evidence_strength — strong, moderate, limited, very_limited or insufficient — computed from the study behind it, never set by hand, plus the verbatim sentence it was drawn from, the paper, the population and dose, and a permalink to check it.
Relations from reference databases (targets, pathways, reactions), each labelled as a hypothesis rather than a reported result.

Evidence strength describes how well the evidence supports a finding. It is not a recommendation, and nothing here is medical advice. No tool returns a product, a price or a link to buy anything, and no tool ranks what to take.

Changed in 0.2.0 (ADR-0103): tool results report evidence_strength as a named level and never a letter, and get_findings takes an evidence_strength floor. The grade field and the grade argument are gone; a call that still sends grade gets an error naming the replacement.

Install

Client	How
Claude (web, desktop)	Settings → Connectors → Add custom connector → `https://catalystproject.ai/mcp`
ChatGPT	Developer mode → add a custom app/connector with `https://catalystproject.ai/mcp`
Claude Code (plugin, adds the server and a skill for presenting evidence strength)	`/plugin marketplace add colorcatalyst/catalyst-mcp` then `/plugin install catalyst@catalyst`
Claude Code (server only)	`claude mcp add --transport http catalyst https://catalystproject.ai/mcp`
VS Code / GitHub Copilot	The Catalyst Evidence Graph extension (VSIX on the releases page), the one-click link on /connect, or `.vscode/mcp.json` below
Cursor	One-click install, or `~/.cursor/mcp.json` below
Gemini CLI	`gemini extensions install https://github.com/colorcatalyst/catalyst-mcp`
Anything else	the JSON below

json

{ "mcpServers": { "catalyst": { "url": "https://catalystproject.ai/mcp" } } }

VS Code's own file takes a slightly different shape:

json

{ "servers": { "catalyst": { "type": "http", "url": "https://catalystproject.ai/mcp" } } }

In this repository

Path	What it is
`server.json`	The entry in the official MCP registry
`.claude-plugin/marketplace.json`, `plugins/catalyst/`	A Claude Code plugin marketplace with one plugin: the server and an `evidence-strength` skill
`gemini-extension.json`, `GEMINI.md`	A Gemini CLI extension
`vscode/`	A VS Code extension that registers the server with Copilot's agent mode

Privacy

The server stores no queries and has no accounts. Rate limits count calls per minute against the client's name and a keyed hash of the network address, never the address itself. Full notice: https://catalystproject.ai/privacy.

Contact

Questions, or something an assistant got wrong from this graph: hello@catalystproject.ai

The code in this repository is MIT-licensed. The graph's content carries the terms on https://catalystproject.ai/terms and per-source licences on https://catalystproject.ai/attribution.

Install

Tools (7)

find_evidencesearch_nodesget_findingsget_findingget_relationsget_reactionsreach

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://catalystproject.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "evidence-graph": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://catalystproject.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.catalystproject/evidence-graph MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

find_evidence

search_nodes

get_findings

get_finding

get_relations

get_reactions

reach

Catalyst evidence graph — MCP server, plugins and extensions

What an assistant gets

Install

In this repository

Privacy

Contact

Install

Remote endpoint

Related servers