Installation¶

searxng-mcp is a standard Python package and a prebuilt container image. Pick the path that matches how you want to run it.

Requirements¶

Python 3.11 – 3.14.
A reachable SearXNG instance — see Backing Platform to deploy one locally, or set USE_RANDOM_INSTANCE=true to select a public instance automatically.

From PyPI (recommended)¶

pip install searxng-mcp

Optional extras¶

The base install is intentionally minimal. Install the extra for what you need:

Extra	Install	Pulls in
`mcp`	`pip install "searxng-mcp[mcp]"`	FastMCP MCP-server runtime (`agent-utilities[mcp]`)
`agent`	`pip install "searxng-mcp[agent]"`	Pydantic-AI agent + Logfire tracing (`agent-utilities[agent,logfire]`)
`all`	`pip install "searxng-mcp[all]"`	The MCP server and the agent together
`test`	`pip install "searxng-mcp[test]"`	`pytest`, `pytest-asyncio`, `pytest-cov`, `pytest-xdist`

# Typical: run the MCP server and the A2A agent
pip install "searxng-mcp[all]"

From source¶

git clone https://github.com/Knuckles-Team/searxng-mcp.git
cd searxng-mcp
pip install -e ".[all]"          # editable install with every extra

With uv:

uv pip install -e ".[all]"
uv run searxng-mcp

Prebuilt Docker image¶

A multi-stage, slim image is published on every release (entrypoint searxng-mcp):

docker pull knucklessg1/searxng-mcp:latest

docker run --rm -i \
  -e SEARXNG_URL=http://your-searxng:8080 \
  knucklessg1/searxng-mcp:latest        # stdio transport (default)

For an HTTP server with a published port and the agent server, see Deployment.

Verify the install¶

searxng-mcp --help
python -c "import searxng_mcp; print(searxng_mcp.__version__)"

Next steps¶

Deployment — run it as a long-lived MCP server (and agent) behind Caddy + DNS.
Usage — call the tool, the Python API, and the console scripts.
Configuration — every environment variable.