pubmed-mcp-server | MCP Server

01 / SERVER DETAIL

Server detail

Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.

An MCP server for retrieving web content and converting HTML into Markdown so language models can read, summarize and process pages more easily.

CapabilitiesmcpsmitheryMCPOpen source

ProtocolModel Context Protocol

Developer ecosystemOpen ecosystem

LicenseMIT / check source

SourceGitHub

COLLECTIONS

Popular MCP2026.03.30Listed

My MCP2026.03.31Listed

Genie2026.03.30Listed

02 / TOOL TESTING

AVAILABLE TOOL

Callable

Fetch a URL from the internet and convert HTML content into Markdown.

PARAMETERS

urlstring, required. The URL to fetch.

max_lengthinteger, optional. Maximum returned characters; defaults to 5000.

start_indexinteger, optional. Start extraction at a character index for chunked reads.

rawboolean, optional. Whether to return the raw content without Markdown conversion.

Tip: the tool may truncate responses. Use pagination parameters such as start_index to read long content in chunks.

03 / SERVICE CONFIGURATION

Remote

{
  "mcpServers": {
    "pubmed-mcp-server": {
      "url": "Generated by the provider after deployment"
    }
  }
}

The Remote endpoint is generated by the provider after deployment; this page does not fabricate an unusable endpoint.

Stdio · mcp.json

{
  "mcpServers": {
    "pubmed-mcp-server": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    }
  }
}

Fetch can run directly with uvx mcp-server-fetch.

03 / WORKFLOW

04 / DISCUSSIONS

Use this space to keep checking source information, usage experience and maintenance status.