mcpField
N
NCBI PubMed MCP by usefulapi

NCBI PubMed MCP by usefulapi

Remote
usefulapi.ioSearch1Updated today

About NCBI PubMed MCP by usefulapi

NCBI PubMed MCP by usefulapi is a hosted MCP server for researchers and literature searchers. It provides read-only PubMed search, article summaries and abstracts, related-article lookup, and database information.

Key features

  1. 01Search PubMed literature
  2. 02Read article summaries and abstracts
  3. 03Find related articles
  4. 04View database information

Use cases

  1. 01Find PubMed papers on a topic
  2. 02Review abstracts and discover related research

MCP support

It exposes read-only PubMed search, article retrieval, and database information tools to MCP clients. Users authenticate their NCBI API key through OAuth.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://pubmed-ncbi-e-utilities.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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 README

NCBI PubMed MCP by usefulapi

Use your NCBI PubMed account from Claude, Cursor, or any MCP client. Search PubMed, read article summaries and abstracts, find similar articles, and read the database's search fields, all read-only. Hosted, no local install: connect with your own credentials.

Live endpoint: https://pubmed-ncbi-e-utilities.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://pubmed-ncbi-e-utilities.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http pubmed-ncbi-e-utilities https://pubmed-ncbi-e-utilities.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "pubmed-ncbi-e-utilities": {
      "url": "https://pubmed-ncbi-e-utilities.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your NCBI PubMed credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/pubmed-ncbi-e-utilities/

On first connect you provide your NCBI API key, created in your NCBI account under Settings → API Key Management. The server validates it and stores it per user. No keys go in config files.

Tools

ToolTypeWhat it does
pubmed_searchreadSearch PubMed
pubmed_summaryreadGet article summaries
pubmed_fetch_abstractsreadGet abstracts
pubmed_relatedreadFind related articles
pubmed_database_inforeadPubMed database info
pubmed_usage_statusmetaUsage status (free-tier meter)
pubmed_request_featuremetaRequest a missing feature
pubmed_upgrademetaUpgrade to Pro (unlimited*)
pubmed_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro (per user)$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with pubmed_upgrade (it returns a Stripe Checkout link). Cancel any time with pubmed_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running pubmed_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

Comments

Markdown supported

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.