1. Conduid
  2. Browser
  3. Crawl4ai MCP Py
MCP server · Browser

Crawl4ai MCP Py

by · github.com/gkzhb/crawl4ai-mcp-py

A collection of MCP Servers

Unclaimed MIT last commit 6 months ago mcp-servermcpfastmcpbrowser
InstallView source
64Good

Scored 3 hours ago · breakdown

About Crawl4ai MCP Py

Crawl4ai MCP Py is an MCP server published by gkzhb in the Browser category: a collection of MCP Servers.

The repository has 2 stars and 0 forks, with the last commit 6 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/gkzhb/crawl4ai-mcp-py

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Crawl4ai MCP Py

Powered by Claude · Grounded in docs

I know everything about Crawl4ai MCP Py. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 3 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

Web Crawl and Search MCP Servers

Common Environment Variables

All MCP servers support the following common environment variables (configured via common-mcp):

  • MCP_TYPE: Transport type ( stdio , sse , http ) - defaults to "stdio"
  • MCP_HOST: Host address for SSE/HTTP modes - defaults to "127.0.0.1"
  • MCP_PORT: Listening port for SSE/HTTP modes - defaults to "8000" or "8001"(more details in project readme file)
  • ENV: Environment mode (development or production) - defaults to "development"
  • LOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR) - defaults to "DEBUG" in development, "INFO" in production
  • MCP_AUTH: Comma-separated auth tokens for authentication (optional)
  • DOTENV_FILE: Path to dotenv file to load environment variables from (optional)

Authentication

When MCP_AUTH is set, you need to include the auth token in the request header when connecting to the MCP server:

Authorization: Bearer <your-token>

Example:

curl -H "Authorization: Bearer my-secret-token" http://localhost:8000/mcp

For SSE type, connect to url http://localhost:8000/sse . For HTTP type, connect to url http://localhost:8000/mcp .

gkzhb-mcp Features

The gkzhb-mcp server provides a unified MCP server that combines multiple tools:

  • crawl4ai: Web crawling and content extraction (convert pages to markdown/HTML)
  • searxng: Web search capabilities using Searxng
  • skills: Agent Skills integration for enhanced AI capabilities

You can selectively enable tools using the MCP_TOOL_LIST environment variable:

# Enable only crawl4ai and searxng
MCP_TOOL_LIST=crawl4ai,searxng uv run gkzhb-mcp

# Enable only skills
MCP_TOOL_LIST=skills uv run gkzhb-mcp

README fetched from the repository 3 hours ago. The original is authoritative.

Questions

About Crawl4ai MCP Py

How do I install Crawl4ai MCP Py?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Crawl4ai MCP Py safe to use with an AI agent?

Its trust score is 64 out of 100 (good). It passes 4 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Crawl4ai MCP Py still maintained?

The last commit was 6 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.