xngmcp
An MCP server that exposes web_search and web_fetch tools, enabling web search via SearXNG and fetching readable public pages.
README
xngmcp
xngmcp gives MCP clients and the terminal two local-web tools: web_search via
SearXNG and web_fetch for readable public pages.
Install
Requires Rust 1.85 or newer. Docker with the Compose plugin is required for the included SearXNG backend.
From a source checkout, install xngmcp and start the backend:
cargo install --path .
./infra/searxng/bootstrap.sh
docker compose --env-file infra/searxng/.env \
-f infra/searxng/compose.yaml up -d --wait
The backend listens on http://127.0.0.1:8080. Confirm it and the CLI work:
curl --fail --silent --show-error http://127.0.0.1:8080/healthz >/dev/null
xngmcp search --limit 5 'Rust MCP SDK'
See the SearXNG guide for configuration, operations, and its integration test. See shell integration to install the generated man pages and shell completions.
Pi
Install and configure the Pi package with its
setup guide. It configures
pi-mcp-adapter to run xngmcp serve and exposes web_search and web_fetch
as direct Pi tools.
Usage
# Search the web
xngmcp search 'Rust MCP SDK'
xngmcp search --json --limit 5 'Rust MCP SDK'
# Fetch readable text or Markdown from a public URL
xngmcp fetch --format text https://doc.rust-lang.org/book/
# Run the stdio MCP server
xngmcp serve
Configure an MCP client to start xngmcp serve with
SEARXNG_URL=http://127.0.0.1:8080. The server exposes web_search and
web_fetch. Use --searxng-url or SEARXNG_URL to select another endpoint.
search --json and fetch --json write a single JSON value to stdout. Errors
and diagnostics go to stderr. Run xngmcp --help for all commands and options.
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.