Skip to main content
Glama
Sign In
deenesjakoruzh
searxng-mcp-server

searxng-mcp-server

by maccam912
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

SearXNG MCP Server

A Model Control Protocol (MCP) server for SearXNG, allowing AI assistants to search the web through a SearXNG instance.

Features

  • Search the web using SearXNG via simple API calls

  • Get information about available search engines

  • Configure search parameters including categories, languages, and safe search settings

Related MCP server: Notes MCP Server

Usage in MCP Configuration

 "searxng-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "https://raw.githubusercontent.com/maccam912/searxng-mcp-server/refs/heads/main/server.py",
        "--url",
        "https://searxng.example.com"
      ]
    }

Docker Usage

You can run this MCP server using Docker:

# Build the Docker image
docker build -t searxng-mcp-server .

# Run the container
# Replace https://searxng.example.com with your actual SearXNG instance URL
docker run -p 8080:8080 searxng-mcp-server

API Tools

Search

def search(query: str, categories: Optional[str] = None, engines: Optional[str] = None, 
           language: Optional[str] = None, page: int = 1, time_range: Optional[str] = None,
           safe_search: int = 1)

Get Available Engines

def get_available_engines()

Local Development

Requirements:

  • Python 3.11+

  • uv (Python package manager)

# Install dependencies
uv sync

# Run the server
uv run server.py --url https://searxng.example.com

Available Tools

2 tools
get_available_enginesB

Get information about available search engines

Inputs: no named parameters. Returns: result

searchC
Search using SearXNG

Args:
    query: The search query
    categories: Optional comma-separated list of categories
    engines: Optional comma-separated list of engines
    language: Optional language code
    page: Page number (default: 1)
    time_range: Optional time range (day, month, year)
    safe_search: Safe search level (0, 1, 2)

Inputs: query (required), categories, engines, language, +3 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: get_available_engines retrieves metadata about search engines, while search performs actual searches. There is no overlap or ambiguity between these functions.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun naming pattern (get_available_engines and search). The naming is straightforward and predictable across the toolset.

    Tool Count2/5

    With only two tools, the server feels under-scoped for a search functionality domain. While the core search operation is present, typical search-related operations like managing preferences, saving searches, or advanced filtering are missing, making the toolset feel thin.

    Completeness2/5

    The toolset is severely incomplete for a search server. It lacks essential operations such as configuring search settings, handling search history, or integrating with other data sources. The surface is minimal and does not cover the expected lifecycle of search interactions.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    Appeared in Searches