PyreCrawl MCP Server

🔥 PyreCrawl — Web Browsing Superpowers for Your AI Agent

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.

PyreCrawl speaks MCP (Model Context Protocol), the standard tool interface for Claude, Cursor, VS Code, Codex, OpenCode, Hermes, and any MCP-compatible agent.

A smart auto-fallback ladder always picks the cheapest method that succeeds:

fast HTTP
    │  (403/503/Cloudflare challenge or empty body)
    ▼
stealth browser (real Chromium + Cloudflare solver)
    │  (still blocked, or the page needs full JS rendering)
    ▼
deep processing (LLM-ready markdown, citations, structured extraction)

⚡ Tools exposed

MCP Resources (read-only state without a tool call): pyrecrawl://cache/stats · pyrecrawl://sessions · pyrecrawl://monitors

MCP Prompts (ready-made playbooks): research(topic) · rag_ingest(site) · watch_page(url)

Env flags

prefer options: "auto" (default ladder) · "fast" (HTTP only) · "stealth" (CF bypass) · "llm" (deep processing).

---

🚀 Install & Use (one-liner)

1. Install

UV (recommended — one command, zero Python setup)

UV is a fast Python package manager that handles Python itself — no need to install Python separately. Get it once:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Learn more about UV →

Then run PyreCrawl directly — no venv, no pip install, no Python download:

uvx pyrecrawl@latest

Or via uv tool install (persistent, recommended for regular use)

uv tool install pyrecrawl

Or via pipx (alternative)

pipx install pyrecrawl

Or via pip into a venv

pip install pyrecrawl

2. One-time browser engines

pyrecrawl setup

This installs Chromium + stealth browser engines (~2 min, one-time).

3. Register with your AI agent

# Auto-detect installed agents and write their MCP configs
pyrecrawl install

# Or target specific agents
pyrecrawl install claude-desktop cursor

# Dry-run to preview what would change
pyrecrawl install --dry-run

Supported agents: claude-desktop, claude-code, cursor, vscode, codex, opencode, hermes.

4. Start chatting

After installing + registering, restart your agent (or start a new session). Then ask:

"Scrape https://example.com and summarize it."

Available tools:

Plus 3 guided prompts: research, rag_ingest, watch_page.

Quick examples

Ask your agent naturally — no special syntax needed:

---

🧠 Skills — Maximize Your Agent's Research Quality

PyreCrawl tools give your agent hands (scrape, crawl, search). But the agent still needs a brain — instructions on when to use which tool, how to chain research passes, and what anti-hallucination rules to follow.

That's what PyreCrawl Skills provides.

Quick setup:

# 1. Install the tools (you already have this)
uvx pyrecrawl@latest

# 2. Add the research skill to your project
git clone https://github.com/SanggonBoy/pyrecrawl-skills.git /tmp/pyrecrawl-skills
cp /tmp/pyrecrawl-skills/pyrecrawl-research/SKILL.md ./CLAUDE.md  # or .cursorrules / AGENTS.md

Without skills: Your agent has powerful tools but improvises usage. With skills: Your agent follows a proven research protocol with anti-hallucination guardrails.

---

📚 Manual config (if pyrecrawl install doesn't match your setup)

Claude Desktop

Config file

• Linux: ~/.config/Claude/claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %AppData%\Claude\claude_desktop_config.json

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

Claude Code

Config file: project-scoped .mcp.json

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

Cursor

Config file: ~/.cursor/mcp.json

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

VS Code / Copilot

Config file: .vscode/mcp.json (project-scoped)

{
  "servers": {
    "pyrecrawl": {
      "command": "uvx",
      "args": ["--from", "pyrecrawl", "pyrecrawl", "serve"],
      "type": "stdio"
    }
  }
}

Codex CLI

Config file: ~/.codex/config.toml

[mcp_servers.pyrecrawl]
command = "uvx"
args = ["--from", "pyrecrawl", "pyrecrawl", "serve"]

OpenCode

Config file: ~/.config/opencode/opencode.json

{
  "mcp": {
    "pyrecrawl": {
      "type": "local",
      "command": ["uvx", "--from", "pyrecrawl", "pyrecrawl", "serve"],
      "enabled": true
    }
  }
}

Hermes

Config file

• Linux/macOS: ~/.hermes/config.yaml
• Windows: %LocalAppData%\hermes\config.yaml

mcp_servers:
  pyrecrawl:
    command: uvx
    args:
      - --from
      - pyrecrawl
      - pyrecrawl
      - serve
    enabled: true

Windows note: uvx must be on PATH. If not, use the full path to uvx.exe (e.g. C:\Users\<you>\AppData\Local\hermes\bin\uvx.exe).

---

🧠 How the ladder chooses

PyreCrawl runs each request through three tiers, stopping at the first one that returns a complete, LLM-ready result:

The agent never has to pick. prefer="auto" does it every call.

Live DOM data with js and wait_for

Some sites keep the data you want in a DOM property (e.g. an <input>'s .value) that JS writes after an XHR — it never appears in the serialized HTML. The scrape tool accepts two stealth-tier params for exactly this:

{
  "url": "https://temp-mail.org/id",
  "prefer": "stealth",
  "wait_for": "document.getElementById('mail').value.includes('@')",
  "js": "document.getElementById('mail').value"
}

• wait_for — a JS predicate expression polled until truthy (bounded by timeout). Use it instead of guessing a sleep for anything that arrives asynchronously.
• js — a JS expression evaluated once the page settles; the value comes back in meta.js_result. Errors are captured in meta.js_error (the page result is still returned, never a crash).

---

📊 Compared to Firecrawl (hosted)

---

🔧 Development

git clone https://github.com/SanggonBoy/PyreCrawl.git
cd PyreCrawl
uv venv --python 3.12 .venv
source .venv/Scripts/activate  # Windows; or .venv/bin/activate on macOS/Linux
uv pip install -e ".[dev]"
python -m playwright install chromium
scrapling install

Run tests

python scripts/selfcheck.py        # real-network smoke test (13 tools + engines)
python scripts/probe_stdio.py      # stdio JSON-RPC probe
python scripts/test_ladder_bug.py  # SPA-shell ladder escalation regression
python scripts/test_js_eval.py     # stealth js/wait_for params regression
python scripts/test_scope_selector.py  # crawl css_selector/max_depth wiring
python scripts/test_link_harvest.py    # map/BFS link purity regression

---

📦 Publish

Maintainers only:

git tag vX.Y.Z
git push origin vX.Y.Z

GitHub Actions builds + uploads to PyPI via trusted publishing.

---

🔔 Stay up to date

PyreCrawl checks PyPI on every startup and reports the latest version — your MCP agent sees this automatically via the health() tool response and can notify you inline.

To check manually:

pyrecrawl version

To upgrade:

pyrecrawl update   # runs: uv tool upgrade pyrecrawl

Get notified of new releases: click Watch → Releases only at the GitHub repo to receive email notifications when a new version is published.

---

[!NOTE] PyreCrawl sends one anonymous usage ping per 24 h at server startup — see Privacy for exactly what's sent and how to opt out.

🔒 Privacy — anonymous usage ping

PyreCrawl phones home once per 24 h with a tiny anonymous ping when the MCP server starts, so we can count real users (DAU/MAU) instead of raw downloads.

Client code: src/pyrecrawl/telemetry.py (~90 lines, stdlib only) · Collector: workers/telemetry/ — a self-hostable Cloudflare Worker + D1, no third-party analytics service.

Opt out any time:

export PYRECRAWL_NO_TELEMETRY=1   # or the industry-standard DO_NOT_TRACK=1

---

📜 Uninstall

# Remove from all agent configs
pyrecrawl uninstall

# Remove the package
uv tool uninstall pyrecrawl

---

🛡️ License

MIT — see LICENSE.