Pyre Crawl MCP Server

One command gives any AI agent the whole web. Scrape, extract, crawl, map, and search - self-hosted, no API keys, no rate limits, no subscription. It runs locally over stdio via the published package.

People who work with crawler, firecrawl alternative and rag and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-11 · ★ 15 · #19 OF 93 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Pyre Crawl

before you install - you'll need

Set PYRECRAWL_NO_TELEMETRY before connecting.

Claude Code

claude mcp add sanggonboy-pyrecrawl -- uvx pyrecrawl

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "sanggonboy-pyrecrawl": {
      "command": "uvx",
      "args": [
        "pyrecrawl"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-09-03 - young repo, little track record yet

license MIT - declared in the repository

pypi package pyrecrawl - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.SanggonBoy is GitHub-verified and matches the repo owner

03 · What Pyre Crawl can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.7.5 · 2026-09-11

Highlights · Anonymous usage telemetry (opt-out, transparent) - counts real users (DAU/MAU) instead of raw download numbers. One tiny ping per 24 h: hashed machine id + version + Python version + OS family. No IP…

v0.7.3 · 2026-09-08

v0.7.3 - Auto-Update Checker · New Features · health() tool returns {current, latest, update_available} - MCP agents see version info automatically · Server startup prints update warning to stderr when a newer release…

v0.7.2 · 2026-09-08

Bug Fix · pyrecrawl setup: resolved scrapling CLI from venv Scripts directory instead of relying on PATH. Fixes FileNotFoundError: no scrapling on Windows (uvx/pip installs where Scripts/ is not on PATH). · pip install…

04 · Who maintains Pyre Crawl

PyreCrawl is maintained by sanggonboy. It's the only MCP server we track from this author; the repo dates to Sep 2026.

05 · Facts

category
web scraping - ranked #19 of 93 actively-maintained web scraping servers as of 2026-09-18.
release cadence
5 releases in the last 90 days (latest 2026-09-11)
registry
io.github.SanggonBoy/PyreCrawl (active, first published 2026-09-03 · 9 versions)
packages
pypi:pyrecrawl

06 · Pyre Crawl FAQ

What is Pyre Crawl?

One command gives any AI agent the whole web. Scrape, extract, crawl, map, and search - self-hosted, no API keys, no rate limits, no subscription. It runs locally over stdio via the published package.

Is Pyre Crawl still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-11 and it shipped 5 releases in the last 90 days. We re-verify nightly.

How do I install Pyre Crawl?

Run `uvx pyrecrawl`. The README documents one environment variable (PYRECRAWL_NO_TELEMETRY) to set first. Set PYRECRAWL_NO_TELEMETRY before connecting. You can also paste the ready-made client config above.

Does Pyre Crawl run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Pyre Crawl

More web scraping MCP servers · Scrape Badger · OpenGraph.io MCP Server · Openinsurance Wiki · Omnisearch · Crawlie

More Python MCP servers · Kafka Sentinel · Veddata · Aippocampus · Billing Gateway · AI Divination Skills · see all