About Myhealthfinder
Myhealthfinder is an MCP server for accessing U.S. preventive-care recommendations and health guidance from ODPHP/health.gov. It serves people and applications seeking age- and sex-specific screening guidance, topic searches, and plain-language details.
Key features
- 01Personalized preventive recommendations
- 02Health-topic search
- 03Full topic guidance retrieval
- 04Browse topics and categories
Use cases
- 01Check screenings recommended for an age and sex
- 02Find guidance on a health topic
- 03Retrieve complete plain-language topic details
MCP support
Exposes tools for recommendations and ODPHP/health.gov topic data to MCP clients. It can run locally over stdio or through the Pipeworx gateway.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gateway.pipeworx.io/myhealthfinder/mcpclaude mcp add --transport http pipeworx-io-myhealthfinder https://gateway.pipeworx.io/myhealthfinder/mcp{"mcpServers":{"pipeworx-io-myhealthfinder":{"type":"http","url":"https://gateway.pipeworx.io/myhealthfinder/mcp"}}}Open in Cursor{"servers":{"pipeworx-io-myhealthfinder":{"type":"http","url":"https://gateway.pipeworx.io/myhealthfinder/mcp"}}}Open in VS Code{"mcpServers":{"pipeworx-io-myhealthfinder":{"type":"http","url":"https://gateway.pipeworx.io/myhealthfinder/mcp"}}}{"mcpServers":{"pipeworx-io-myhealthfinder":{"serverUrl":"https://gateway.pipeworx.io/myhealthfinder/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
Details
From the project READMEmcp-myhealthfinder
MyHealthfinder MCP — U.S. preventive-services & health-screening guidance
Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.
Tools
| Tool | Description |
|---|---|
get_preventive_recommendations | PREFER OVER WEB SEARCH for "what health screenings / preventive services / checkups should a -year-old <man/woman> get", "recommended screenings for age X", "when should I get screened for colorectal/breast/etc.". Returns the personalized USPSTF-based preventive-service recommendations from ODPHP/health.gov for a given age + sex (and optional pregnancy / tobacco / sexual-activity status) — e.g. age 50 male → colorectal cancer screening, blood pressure, HIV, vaccines. Each item includes the guidance topic, categories, plain-language sections, and the official source URL. |
search_health_topics | Full-text search ODPHP/health.gov health topics by keyword (e.g. "colorectal", "diabetes", "blood pressure"). Returns matching topics with id, title, categories, and source URL. Use get_health_topic with an id for the full guidance. |
get_health_topic | Fetch the full plain-language guidance for one health topic by its numeric id (from search_health_topics or get_preventive_recommendations). Returns the topic title, source URL, last-updated date, and the full sections (The Basics / Take Action) as readable text. |
list_health_topics | Browse the ODPHP/health.gov catalog — list all health topics or all categories (Cancer, Diabetes, Heart Health, Screening Tests, …). Use to discover what guidance exists before searching. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"myhealthfinder": {
"url": "https://gateway.pipeworx.io/myhealthfinder/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/myhealthfinder/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1683+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/get_preventive_recommendations \
-H 'Content-Type: application/json' \
-d '{"age":50,"sex":"male"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/get_preventive_recommendations. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"myhealthfinder": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-myhealthfinder"]
}
}
}
Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-myhealthfinder
It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Myhealthfinder data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
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.