TdxClaw-compatible MCP Server
A standalone local MCP server that provides web fetching, searching, and HTTP request tools without requiring TdxClaw installation.
README
TdxClaw-compatible MCP Server
独立的本地 MCP Server,复刻 TdxClaw (openclaw) 的数据请求能力。无需安装 TdxClaw 即可让你的 agent 通过 MCP 协议调用网页抓取、搜索和 HTTP 请求工具。
提供的工具
| 工具 | 说明 |
|---|---|
web_fetch |
抓取网页内容,自动转换为 Markdown 或纯文本,带 SSRF 防护 |
web_search |
使用 DuckDuckGo 搜索网页,无需 API Key |
http_request |
通用 HTTP 请求工具,支持 GET/POST/PUT/PATCH/DELETE,自定义 Headers 和 Body |
快速开始
前置条件
- uv(TdxClaw 自带:
C:\TdxClaw\resources\bin\uv.exe) - 或 Python 3.10+
方式一:使用启动脚本(推荐)
start.cmd
首次运行会自动创建虚拟环境并安装依赖。
方式二:手动运行
cd tdx-mcp-server
# 创建虚拟环境并安装依赖
uv venv
uv pip install "mcp[cli]>=1.0.0" "httpx>=0.27.0" "beautifulsoup4>=4.12.0" "markdownify>=0.13.0" "duckduckgo-search>=6.0.0"
# 启动 stdio 模式(大多数 MCP 客户端)
.venv\Scripts\python.exe server.py
# 或启动 HTTP 模式(openclaw 风格的 agent)
.venv\Scripts\python.exe server.py --http --port 31868
连接你的 Agent
Stdio 模式(适用于大多数 MCP 客户端)
在你的 agent 的 MCP 配置中添加:
{
"mcpServers": {
"tdx-mcp": {
"command": "C:\\path\\to\\tdx-mcp-server\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\tdx-mcp-server\\server.py"]
}
}
}
HTTP 模式(适用于 openclaw 等支持 HTTP MCP 的 agent)
先启动 HTTP 服务:
.venv\Scripts\python.exe server.py --http --port 31868
然后在 agent 配置中指向 http://127.0.0.1:31868/mcp。
OpenClaw 配置示例
在 openclaw.json 中添加:
{
"mcp": {
"servers": {
"tdx-mcp": {
"type": "http",
"url": "http://127.0.0.1:31868/mcp"
}
}
}
}
或使用 stdio:
{
"mcp": {
"servers": {
"tdx-mcp": {
"command": "C:\\path\\to\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\server.py"]
}
}
}
}
工具参数说明
web_fetch
{
"url": "https://example.com",
"extractMode": "markdown",
"maxChars": 20000
}
web_search
{
"query": "搜索关键词",
"maxResults": 5,
"region": "cn-zh"
}
http_request
{
"url": "https://api.example.com/data",
"method": "POST",
"headers": {
"Authorization": "Bearer YOUR_TOKEN",
"Content-Type": "application/json"
},
"body": "{\"key\": \"value\"}",
"timeout": 30,
"maxChars": 20000
}
与 TdxClaw MCP 的对比
| 特性 | TdxClaw MCP | 本 Server |
|---|---|---|
| 传输协议 | HTTP (Streamable HTTP) | Stdio + HTTP |
| 默认端口 | 31868 | 31868 (HTTP 模式) |
| web_fetch | ✅ | ✅ |
| web_search | ✅ (需配置 API Key) | ✅ (DuckDuckGo, 免费) |
| http_request | ❌ | ✅ |
| 认证 | Bearer Token | 无(本地使用) |
| SSRF 防护 | ✅ | ✅ |
| 依赖 | TdxClaw 完整安装 | 仅 Python + 几个包 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.