onion-search-mcp
Enables searching and exploring the dark web (.onion) via a gMCP-compatible server, with tools to search multiple engines, fetch onion pages, check status, and extract links.
README
onion-search-mcp
guMCP-zgodny serwer Model Context Protocol do wyszukiwania i eksploracji
dark webu (.onion). Idealny do podłączenia do Gumloopa jako
Custom MCP Server.
Struktura repo
onion-search-mcp/
├── src/servers/onion-search/ # serwer w konwencji guMCP
│ ├── main.py # create_server / list_tools / call_tool
│ ├── config.yaml # metadane + tools (jak perplexity)
│ ├── README.md # dokumentacja serwera
│ └── assets/icon.jpeg
├── standalone_server.py # Streamable HTTP + SSE w jednym pliku
├── Dockerfile # python + tor + uvicorn = jeden kontener
├── requirements.txt
└── README.md # ten plik
Tools (6)
list_search_engines– co potrafi serwersearch_ahmia– wyszukiwarka clearnet/onion Ahmiisearch_dark_web– multi-engine (Ahmia + Torch)fetch_onion– pobiera tekst .onion przez Torcheck_onion_status– ping .onionextract_onion_links– regex v2/v3 .onion z tekstu
Szybki start lokalnie
# 1. Zależności
pip install -r requirements.txt
# 2. Tor (do narzędzi .onion)
sudo systemctl start tor # albo: tor &
# 3. Serwer
python standalone_server.py --host 0.0.0.0 --port 8080
# 4. Smoke test
curl http://127.0.0.1:8080/health
Endpoint MCP dla klientów Streamable HTTP: http://127.0.0.1:8080/mcp.
Deploy na Gumloopa
- Zbuduj obraz:
docker build -t onion-search-mcp . - Wystaw publiczne HTTPS (Render, Fly.io, Railway, AWS App Runner, Cloudflare Tunnel… cokolwiek). HTTP jest blokowany przez Gumloop.
- (opcjonalnie) ustaw
MCP_BEARER_TOKEN=<sekret>żeby wymagać auth. - W Gumloop: Settings → Credentials → MCP Server → Add credential
- URL:
https://<twoj-host>/mcp - Access Token: ten sam
MCP_BEARER_TOKEN
- URL:
- Add tools → MCP Server → Custom →
onion-searchna agencie.
Integracja z głównym repo guMCP
Folder src/servers/onion-search/ jest 1:1 zgodny z konwencją guMCP –
wystarczy go skopiować do swojego forka:
cp -r src/servers/onion-search /path/to/guMCP/src/servers/
python src/servers/local.py --server onion-search --user-id local
Auto-discovery w remote.py::discover_servers() znajdzie folder
automatycznie.
Bezpieczeństwo
- Cały ruch do .onion idzie przez Tor SOCKS5 (
TOR_SOCKS_PROXY). - Domyślnie Ahmia uderzana jest po clearnet (HTTPS, bez Tora) – szybkie i bezpieczne.
- Ahmia filtruje CSAM; Torch/Haystak – nie. Stosuj odpowiednie filtry po stronie wywołującego.
- Standalone server obsługuje Bearer-token (
MCP_BEARER_TOKEN).
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.