Wraps the NCBI E-utilities API so Claude can search and retrieve records from PubMed, Gene, Nucleotide, and the rest of the Entrez database ecosystem. You get six core operations: einfo for database metadata, esearch for running queries and getting UIDs, esummary for quick record overviews, efetch for full records in XML/GenBank/FASTA formats, elink for cross-database relationships, and egquery for searching across all databases at once. Hosted via Pipeworx's gateway with streamable HTTP transport, so no local setup. Useful when you need Claude to pull literature references, gene sequences, or protein data directly from NCBI without manual API wrangling.
NCBI E-utilities MCP — federated Entrez search/fetch.
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
einfo | Database info / field list. |
esearch | Search a database → uid list. |
esummary | Summary records by uid. |
efetch | Full records. Returns text (XML/GenBank/FASTA/…) per rettype. |
elink | Links across databases. |
egquery | Global query across all Entrez databases. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"ncbi-eutils": {
"url": "https://gateway.pipeworx.io/ncbi-eutils/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Ncbi Eutils data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp