MCP.Market

Searxng MCP server

by aicrafted·io.github.aicrafted/searxng-mcp·v1.0.0·9 stars

MCP server for SearXNG aggregator — web search across multiple engines via Model Context Protocol

C68/100grade C
What users say
No reviews yet
Be the first
Safety scan
C68/100

full report

Adoption
New

9 stars

Reviews

Write one

Nobody has reviewed Searxng yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Searxng tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 135 days ago8/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 68/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Searxng compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
68/100
higher than 33% of 4,460 AI and agents servers
GitHub stars
9
more than 83% of 2,711 AI and agents servers

Install Searxng in Claude Code, Cursor or VS Code

claude mcp add searxng-mcp -- docker run -i --rm ghcr.io/aicrafted/searxng-mcp:latest
Add to Cursor

What the publisher says

From the Searxng repository's README, as published. We do not edit it. Read it on GitHub

SearXNG MCP Server

A Model Context Protocol (MCP) server that provides web search capabilities by integrating with a SearXNG instance.

Features

  • Web Search: Perform powerful aggregated searches across multiple engines.
  • Discovery: Programmatically retrieve available categories and engines.
  • Stateless HTTP: Compatible with any standard JSON-RPC client.
  • Flexible Configuration: Supports environment variables and command-line arguments.

Example of compose.yml to run SearXNG with MCP server

services:
  searxng:
    image: searxng/searxng:latest
    ports:
      - "${SEARXNG_PORT:-8080}:8080"
    volumes:
      - "${SEARXNG_VOL_CONFIG:-searxng-config}:/etc/searxng/"
      - "${SEARXNG_VOL_DATA:-searxng-data}:/var/cache/searxng/"
    restart: always

  searxng-mcp:
    image: ghcr.io/aicrafted/searxng-mcp:latest
    restart: unless-stopped
    depends_on:
      # Ensure SearXNG starts before the MCP server
      - searxng
    environment:
      SEARXNG_URL: "${SEARXNG_URL:-http://searxng:8080}"
      MCP_HOST: "${MCP_HOST:-127.0.0.1}"
      MCP_PORT: "${MCP_PORT:-32123}"
      MCP_TRANSPORT: "${MCP_TRANSPORT:-http}"
      MCP_ALLOWED_HOSTS: "${MCP_ALLOWED_HOSTS:-localhost:*,127.0.0.1:*}"
      MCP_ALLOWED_ORIGINS: "${MCP_ALLOWED_ORIGINS:-http://localhost:*,http://127.0.0.1:*}"
      MCP_DISABLE_DNS_REBINDING_PROTECTION: "${MCP_DISABLE_DNS_REBINDING_PROTECTION:-false}"
    ports:
      - "${MCP_PORT:-32123}:${MCP_PORT:-32123}"

volumes:
  searxng-config:
  searxng-data:

Important: Enable JSON responses in your SearXNG settings.yml, otherwise the MCP server cannot read search results:

yaml

search:

formats:

- html

- json

Example .env

# SearXNG url should be visible by the MCP server inside docker, so use internal service port here
SEARXNG_URL=http://searxng:8080
# Public SearXNG port
SEARXNG_PORT=8080
# Searxng config and data volumes, start with "./" if You want to bind dir instead using volume
SEARXNG_VOL_CONFIG=searxng-config
SEARXNG_VOL_DATA=searxng-data

# MCP server host, port and transport ("stdio", "sse", "http")
MCP_HOST=127.0.0.1
MCP_PORT=32123
MCP_TRANSPORT=http

# MCP DNS rebinding protection (see https://github.com/modelcontextprotocol/python-sdk/issues/1798 for details)
MCP_ALLOWED_HOSTS=localhost:*,127.0.0.1:*
MCP_ALLOWED_ORIGINS=http://localhost:*,http://127.0.0.1:*
# MCP_DISABLE_DNS_REBINDING_PROTECTION=true

MCP client config

HTTP transport (recommended)

{
  "mcpServers": {
    "searxng": {
      "type": "http",
      "url": "http://localhost:32123/mcp"
    }
  }
}

SSE transport

{
  "mcpServers": {
    "searxng": {
      "type": "sse",
      "url": "http://localhost:32123/sse"
    }
  }
}

Note: SSE transport uses the /sse endpoint, not /mcp. HTTP transport uses /mcp.

Prerequisites for run from sources

  • Python 3.10+
  • A running SearXNG instance.

Installation

  1. Clone the repository and navigate to the directory.
  2. Install dependencies:
pip install -r requirements.txt
  1. Set up your .env file (optional).

Configuration

The server reads configuration from command-line arguments and environment variables. Command-line arguments override the corresponding defaults used at startup.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Searxng: common questions

Is Searxng MCP server safe?
With care: it is graded C, so read the findings first (68/100). Read the Searxng safety report
How do I install Searxng?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Searxng need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Searxng maintained?
The last commit was 172 days ago (2026-05-16). The latest release is v1.0.0.
What can I use instead of Searxng?
Servers from other publishers that do the same job: Robin: AI-Powered Dark Web OSINT MCP server, agent-device MCP server and LLM Sandbox MCP server.
How does Searxng compare with other AI and agents MCP servers?
safety score 68/100 (higher than 33% of 4,460 AI and agents servers); github stars 9 (more than 83% of 2,711 AI and agents servers). Full comparison.

Alternatives to Searxng

Same job from other publishers: the closest match first, then the best rated.

  • Robin: AI-Powered Dark Web OSINT
    Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.
    A
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • LLM Sandbox
    Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
    A
  • Summer Engine
    The game engine built for AI. Any agent makes a multiplayer game and publishes it.
    B
  • DCC-MCP Core
    Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
    A