広告掲載
MCP.so
ログイン

MCP Server

@tcpipuk

リポジトリ

基本情報

カテゴリ

その他

ライセンス

GPL-3.0

トランスポート

stdio

作者

tcpipuk

MCP Server について

Provides tools to clients over the Model Context Protocol

MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-server-tcpipuk": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Server?

An MCP (Model Context Protocol) server that gives AI assistants the ability to safely access websites and search the web through two tools: Search and Web. Designed for users of Claude Desktop, LibreChat, and other MCP-compatible clients.

How to use MCP Server?

Run the server via Docker using the provided docker-compose.yml, or locally with Python 3.13+ and uv. Set the required SEARXNG_QUERY_URL environment variable pointing to your SearXNG instance. Choose SSE mode (network) for clients like LibreChat or stdio mode for direct connections like Claude Desktop.

Key features of MCP Server

  • Search the web via a SearXNG instance
  • Access websites and convert content to markdown
  • Get raw web content or extract links
  • SSE mode for networked client connections
  • stdio mode for direct local connections
  • Clear error messages and progress feedback

Use cases of MCP Server

  • Enable AI assistants to search for current web information
  • Let AI assistants access and process website content
  • Integrate web search capabilities into Claude Desktop
  • Add web browsing features to LibreChat workflows

よくある質問

1

What tools does the server offer?

Two tools: Search (searches the web via SearXNG) and Web (accesses websites, converts pages to markdown, gets raw content, or extracts links).

2

How can I run the server?

Recommended method is Docker with `docker-compose.yml`. Alternatively, run locally using Python 3.13+ and `uv` with `uv sync` then `mcp-server` (stdio) or `mcp-server --sse-host 0.0.0.0 --sse-port 3001` (SSE).

3

How do I connect to the server?

Two modes: network connection via SSE (for LibreChat and other networked clients) or direct connection via stdio (for local testing or Claude Desktop).

4

What environment variables are required?

`SEARXNG_QUERY_URL` (URL to your SearXNG instance's Search API) is always required. Optional: `SSE_HOST`, `SSE_PORT`, and `USER_AGENT`.

5

What are the runtime dependencies?

Docker for the containerized approach, or Python 3.13+ with `uv` for local runs. A running SearXNG instance is required for search functionality.

コメント

「その他」の他のコンテンツ

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

ICSS

chokcoco

不止于 CSS

20.7K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

広告掲載