MCP-searxng
Language:
Python
Stars:
57
Forks:
9
MCP-searxng
An MCP server for connecting agentic systems to search systems via searXNG.
Tools
Search the web with SearXNG
Prompts
search(query: str) -> f"Searching for {query} using searXNG"
Usage
via uvx
- configure your client JSON like
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": [
"mcp-searxng"
]
}
}
}
via git clone
- Add the server to claude desktop (the entrypoint is main.py)
Clone the repo and add this JSON to claude desktop
you can run this server with uvx mcp-searxng
, or use a local copy of the repo
{
"mcpServers": {
"searxng": {
"command": "uv",
"args": [
"--project",
"/absoloute/path/to/MCP-searxng/",
"run",
"/absoloute/path/to/MCP-searxng/mcp-searxng/main.py"
]
}
}
}
you will need to change the paths to match your environment
Custom SearXNG URL
-
set the environment variable
SEARXNG_URL
to the URL of the searxng server (default ishttp://localhost:8080
) -
run your MCP client and you should be able to search the web with searxng
Note: if you are using claude desktop make sure to kill the process (task manager or equivalent) before running the server again
Publisher info
TerminalMan
Computer Science undergraduate passionate about Artificial Intelligence, self-hosted software solutions, and automation.
More MCP servers built with Python
Unified Context Layer (UCL) is a multi-tenant Model Context Protocol (MCP) server that enables AI agents, automation platforms, and applications to connect to over 1,000 SaaS tools—such as Slack, Jira, Gmail, Shopify, Notion, and more—via a single standardized /command endpoint.
Bridge the gap between design and code. Send pixel-perfect website components directly to Cursor or Claude Code using Model Context Protocol (MCP). No more screenshots or descriptions needed.