Pubcrawl MCP Server

by nickjlamb Your server? Claim it

local only

Pubcrawl runs on your own machine — the client starts it, so there is no endpoint to ping. 106 installs a week from npm. Last commit 16 Oct 2026.

PubMed & Europe PMC literature search, US/UK drug labelling, and clinical trials for AI assistants.

Installs per day peak 325 · avg 27 · -74% w/w

a month agotoday

106

Installs / week

npm · @pharmatools/pubcrawl

Stars

0 open issues

16 Oct 2026

Last commit

8 releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Pubcrawl every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add pubcrawl -- npx -y @pharmatools/pubcrawl

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pubcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/pubcrawl"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.pubcrawl]
command = "npx"
args = ["-y", "@pharmatools/pubcrawl"]

.cursor/mcp.json

{
  "mcpServers": {
    "pubcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/pubcrawl"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "pubcrawl": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/pubcrawl"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: NCBI_API_KEY (NCBI API key for higher rate limits (10 req/s vs 3 req/s). Optional — get one free at https://www.ncbi.nlm.nih.gov/account/).

Alternatives to Pubcrawl

same job, measured the same way

Google Researcher

by zoharbabin

MCP server providing Google Search, web scraping, and multi-source research tools for AI assistants

local only

Kijiji Scraper & Tracker (listings, price drops)

by akhilrajesh213

Kijiji listings for AI agents: search by keyword, city and category; price drops, cars, rentals.

answering

SpiderLook

by spiderlook

Competitor intelligence for AI assistants: daily scans of rivals' posts, ads, and sites.

answering

Craigslist Scraper & Tracker (cars, housing)

by akhilrajesh213

Craigslist listings for AI agents: search by keyword, city, state and category; cars, rentals.

answering

SearXNG MCP Server

by bumbarasch

Self-hosted SearXNG metasearch for MCP clients: 13 tools, citation refs, deep search and crawling.

221 installs/wk local only

Geolint

by iliasabk

ESLint for AI search: audits AI-crawler access, llms.txt, schema and citability.

87 installs/wk local only

ScrapeWhale

by scrapewhale

Web data for marketing agents: traffic, ads, social profiles, search, and any URL as markdown.

answering

Olostep MCP Server

by olostep

Live web search, scraping and crawling API for AI. Get structured, LLM-ready data from any site.

1 489 installs/wk answering

Pubcrawl — questions

Answers built from our own checks of this server.

Why is there no uptime for Pubcrawl?

Pubcrawl runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @pharmatools/pubcrawl was installed 106 times last week.

How do I connect Pubcrawl?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @pharmatools/pubcrawl straight from npm; nothing to host, nothing to sign up for.

How many people use Pubcrawl?

The npm package @pharmatools/pubcrawl was installed 106 times in the last week. Week over week that is -74%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Pubcrawl open source?

Yes — it is published under the MIT licence, written in TypeScript and 15 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.