MCP Catalogs
Home

MetaSearchMCP

by gefsikatsinelou·44·Score 46

A metasearch MCP server that aggregates results from multiple providers with normalized JSON output.

searchai-llmdeveloper-tools
2
Forks
0
Open issues
this month
Last commit
2d ago
Indexed

Overview

MetaSearchMCP is a comprehensive metasearch backend that provides both an HTTP API and MCP server interface for AI agents. It aggregates search results from numerous providers including Google, DuckDuckGo, GitHub, Stack Overflow, and academic sources. The server normalizes results into a stable JSON schema with deduplication, provider fallback, and structured metadata. It's built with Python FastAPI and offers concurrent search execution with timeout isolation and partial failure handling.

Try asking AI

After installing, here are 3 things you can ask your AI assistant:

you:LLM agents performing web research with normalized search results across multiple providers
you:Building custom search applications with fallback to different search engines
you:Academic research workflows combining Google Scholar, arXiv, and other academic sources

When to choose this

Choose this for comprehensive metasearch needs when you want to avoid vendor lock-in and need broad coverage across multiple search engines with a consistent JSON interface.

When NOT to choose this

Avoid this if you need real-time search results, as some providers use scraping that may be rate-limited, or if you require authentication for all search queries.

Tools this server exposes

7 tools extracted from the README
  • search_web

    Search across multiple web providers with filtering options

  • search_google

    Search specifically through Google providers

  • search_academic

    Search academic sources like arXiv, PubMed, and Semantic Scholar

  • search_github

    Search repositories and issues on GitHub

  • compare_engines

    Compare results from different search engines

  • search_finance

    Search financial data and markets

  • search_code

    Search code repositories and packages

Comparable tools

searxngduckduckgo-apiserpapisearchapi

Installation

Installation

One-command local install:

python scripts/install.py

Manual install:

git clone https://github.com/gefsikatsinelou/MetaSearchMCP
cd MetaSearchMCP
pip install -e ".[dev]"

Claude Desktop Configuration

Add this to your Claude Desktop config.json:

{
  "mcpServers": {
    "MetaSearchMCP": {
      "command": "metasearchmcp-mcp",
      "env": {
        "ALLOW_UNSTABLE_PROVIDERS": "true",
        "SERPBASE_API_KEY": "your_key",
        "SERPER_API_KEY": "your_key"
      }
    }
  }
}

Compare MetaSearchMCP with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.