Fully decentralized P2P search engine for LLMs via MCP
Fully decentralized P2P search engine for LLMs via MCP
Fully Decentralized P2P Search Engine for LLMs
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"infomesh": {
"command": "uvx",
"args": ["infomesh", "mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PEER_ID | Configuration value read at startup. | Optional |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Ranks the best AI tool or API per task: transcription, TTS, web search, scraping and OCR.
Web search and page extraction across several independent search providers.
One key to 1,000+ paid data APIs: enrichment, SEO/SERP, scraping, places, news. Pay per call.
FrankenClaw is a minimal framework for building MCP tools. Drop a Python file in `tools/`, write one async function with a docstring, flip it on in