MetaSearchMCP
Reduces latency and cost of LLM-powered search by aggregating multiple engines with fallback logic, enabling reliable real-time information retrieval for age…
Python FastAPI metasearch backend with an MCP server over stdio for Claude Desktop and similar clients. Aggregates results from many providers (Google via direct scraping or SerpBase/Serper keys, DuckDuckGo, Brave, arXiv, PubMed, package registries, and more), normalizes them into a stable JSON schema, deduplicates across engines, and tolerates per-provider failures with timeout isolation and fallback.
- Ask Claude to search across multiple engines and return deduplicated results in structured JSON format.
- Automate fallback searches when primary search provider fails during agent workflows.
- Generate aggregated search results from Google and alternative sources for competitive analysis.
Reduces latency and cost of LLM-powered search by aggregating multiple engines with fallback logic, enabling reliable real-time information retrieval for agent workflows without vendor lock-in.
Engineering teams building AI agents requiring multi-source search with fault tolerance and structured output formatting.
https://github.com/gefsikatsinelou/MetaSearchMCP
By gefsikatsinelou
How to Get It
git clone https://github.com/gefsikatsinelou/MetaSearchMCP && cd MetaSearchMCP && python scripts/install.py
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Search across multiple engines and return deduplicated results in structured JSON format
Trust Signals Auto-scanned
Data & Access
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 52 GitHub stars; 4 contributors; last commit 3d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 52 GitHub stars; 4 contributors; last commit 3d ago; license MIT.