About Catalyst evidence graph
Catalyst evidence graph is a curated graph of research findings about compounds, nutrients, supplements, and foods in the human body. It is for assistants and editors that need sourced findings with evidence levels, study details, and references; relations from reference databases are marked as hypotheses.
Key features
- 01Findings by compound or outcome
- 02Named evidence-strength levels
- 03Verbatim source sentences and paper details
- 04Population and dose information
- 05Permalinks to check sources
- 06Reference-database relations labeled as hypotheses
Use cases
- 01Look up research on a compound
- 02Review evidence for a health outcome
- 03Check a finding against its cited paper
- 04Distinguish hypotheses from reported findings
MCP support
Provides read-only evidence-graph tools over Streamable HTTP without an account or key. Findings include evidence strength and source details; the service does not provide recommendations or medical advice.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://catalystproject.ai/mcpclaude mcp add --transport http ai-catalystproject-evidence-graph https://catalystproject.ai/mcp{"mcpServers":{"ai-catalystproject-evidence-graph":{"type":"http","url":"https://catalystproject.ai/mcp"}}}Open in Cursor{"servers":{"ai-catalystproject-evidence-graph":{"type":"http","url":"https://catalystproject.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-catalystproject-evidence-graph":{"type":"http","url":"https://catalystproject.ai/mcp"}}}{"mcpServers":{"ai-catalystproject-evidence-graph":{"serverUrl":"https://catalystproject.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
7| Parameter | Type | Required | Description |
|---|---|---|---|
| about | string | No | Optional: the specific effect or outcome asked about (e.g. "sleep", "blood pressure"), or a node id. |
| limit | integer | No | Findings to return, strongest evidence first. |
| query | string | Yes | The substance or outcome the person asked about, in their words (e.g. "magnesium", "vitamin D", "sleep"), or a node id. |
| detail | enum | No | 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.brief | full |
| evidence_strength | enum | No | Optional floor: only findings with at least this evidence strength.strong | moderate | limited | very_limited | insufficient |
Details
From the project READMECatalyst 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_limitedorinsufficient— 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 |
{ "mcpServers": { "catalyst": { "url": "https://catalystproject.ai/mcp" } } }
VS Code's own file takes a slightly different shape:
{ "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: [email protected]
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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.