MCP server for CITED Health — query supplement evidence from Claude, Cursor, and Windsurf
Project description
citedhealth-mcp
MCP server for CITED Health — query evidence-based supplement data directly from Claude, Cursor, and Windsurf. Ask your AI assistant about ingredient evidence grades, PubMed papers, and health conditions backed by peer-reviewed research.
Browse the evidence at citedhealth.com — grades for 74 ingredients, 30 conditions, and 2,881 PubMed papers.
Table of Contents
- Install
- Configure
- Available Tools
- Example Conversations
- Evidence Grades
- Environment Variables
- Also Available
- License
Install
pip install citedhealth-mcp
Or with uvx (no install needed):
uvx citedhealth-mcp
Configure
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"citedhealth": {
"command": "uvx",
"args": ["citedhealth-mcp"]
}
}
}
Or if installed with pip:
{
"mcpServers": {
"citedhealth": {
"command": "citedhealth-mcp"
}
}
}
Cursor
Edit ~/.cursor/mcp.json:
{
"mcpServers": {
"citedhealth": {
"command": "uvx",
"args": ["citedhealth-mcp"]
}
}
}
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"citedhealth": {
"command": "uvx",
"args": ["citedhealth-mcp"]
}
}
}
Available Tools
| Tool | Description |
|---|---|
search_ingredients |
Search supplement ingredients by name or category |
get_ingredient |
Get detailed info: mechanism, dosage, forms |
search_evidence |
Look up the evidence grade for an ingredient-condition pair |
get_evidence |
Get a specific evidence link by ID |
search_papers |
Search PubMed-indexed papers by title or year |
get_paper |
Get full paper details by PubMed ID |
Example Conversations
Once configured, ask your AI assistant:
- "What is the evidence for biotin and hair loss?"
- "Search for melatonin supplements and sleep research"
- "Find PubMed papers about ashwagandha and anxiety from 2023"
- "What ingredients are in the vitamins category?"
- "Get details about PMID 12345678"
The server will call the CITED Health API and return structured evidence grades, study counts, and paper metadata.
Evidence Grades
CITED Health uses an A-F grading system based on the quality and consistency of peer-reviewed evidence:
| Grade | Label | Criteria |
|---|---|---|
| A | Strong Evidence | Multiple RCTs/meta-analyses, consistent positive results |
| B | Good Evidence | Some RCTs or strong observational studies |
| C | Mixed Evidence | Conflicting results or limited study quality |
| D | Weak Evidence | Mostly observational, small sample sizes |
| F | No Evidence | No credible studies supporting the claim |
Environment Variables
| Variable | Default | Description |
|---|---|---|
CITEDHEALTH_BASE_URL |
https://citedhealth.com |
Override API base URL (for testing or self-hosted) |
Also Available
| Package | Install | Description |
|---|---|---|
| citedhealth-mcp | pip install citedhealth-mcp |
This package — MCP server for AI assistants |
| citedhealth | pip install citedhealth |
Python client for direct API access |
License
MIT License — see LICENSE for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file citedhealth_mcp-0.2.0.tar.gz.
File metadata
- Download URL: citedhealth_mcp-0.2.0.tar.gz
- Upload date:
- Size: 7.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.9 {"installer":{"name":"uv","version":"0.10.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3ab18d1029b0096e31a32736dfdc1c8c7b0e918fc73a4a78f782a789933d87eb
|
|
| MD5 |
f734bdecc637037b612f41f3f611258f
|
|
| BLAKE2b-256 |
41178dab8383b5c79d4e1c16db0fdc836d75ae38cd154bfb4b251b97811c2b21
|
File details
Details for the file citedhealth_mcp-0.2.0-py3-none-any.whl.
File metadata
- Download URL: citedhealth_mcp-0.2.0-py3-none-any.whl
- Upload date:
- Size: 6.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.9 {"installer":{"name":"uv","version":"0.10.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5efdeec03e2810afbd15af864d41045f990f58a98536b4036fe1b23dbd154e95
|
|
| MD5 |
f2f614ebca57b60637c54308a101ae62
|
|
| BLAKE2b-256 |
3df5387e927700c39b6d328d6386ea1954baada0e7ec3b239e07b66953522114
|