mcp-server

crawl4ai-mcp-server

Name: crawl4ai-mcp-server
Author: weidwonder

用于提供给本地开发者的 LLM的高效互联网搜索&内容获取的MCP Server，节省你的token

155 stars34 forksPythonUpdated 1/23/2026100% free · open source

What it does

Provides a local MCP server that lets your LLM fetch and parse web pages efficiently, reducing token usage.

When to use it

•Your AI product needs up‑to‑date web content but you want to avoid sending full pages to the LLM.
•You run a private LLM and must keep all data processing on‑premise for compliance.
•You need a fast, reusable API for web‑scraping that returns clean text, HTML, or metadata.

Ready-to-paste prompt

curl -X POST http://localhost:8000/api/crawl \
  -H "Content-Type: application/json" \
  -d '{"url": "https://news.ycombinator.com/", "extract": "text", "max_depth": 1}'

Heads up: The server requires an OpenAI API key for the default "llm_extractor" mode; without setting `OPENAI_API_KEY` the endpoint will return a 500 error.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/crawl4ai-mcp-server && curl -fsSL https://workflowstacks.com/api/skills/crawl4ai-mcp-server/claude-skill -o ~/.claude/skills/crawl4ai-mcp-server/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How crawl4ai-mcp-server works

Codeflow

Free to inspect

Crawl4ai-mcp-server is a tiny Python project (~400 lines across 4 code files). Setup is light: installs like a normal app. Reading the code is optional. Last commit 9 months ago, MIT license, has a test suite.

Size

Tiny codebase

~400 lines · 4 code files · 3 min skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python · Docker

No API keys detected

Python 96%Dockerfile 4%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
src/index.py
Where the program starts running
3
pyproject.toml
Dependencies and the commands it exposes

What's in each folder

src/Core code — the actual logic2 files

READMEHas testsThin docsNo CIDocker readyMIT licenseLast update 9 mo ago

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/crawl4ai-mcp-server && curl -fsSL https://workflowstacks.com/api/skills/crawl4ai-mcp-server/claude-skill -o ~/.claude/skills/crawl4ai-mcp-server/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

weidwonder

Language

Python