8639 Model Context Protocol servers — searchable, rated, ready to install.
Context-aware code retrieval MCP server — ranked, gated results for AI coding agents
Search and discover Google Apps Script libraries with AI-generated summaries
Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.
Search 13,000+ x402-enabled APIs from your AI agent. Powered by x402search.xyz
Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
Local stdio MCP bridge for archive publishing, retrieval, and governance evidence.
Remote jobs: job search, salary data and application tracking, or post a job and hire candidates
Korean public official asset disclosure data (공직자 재산공개) - search and retrieve assets
Bi-temporal AI memory. 56 tools, knowledge graph, semantic search. EU-hosted, free tier.
Sourced Italian tax tools for AI agents: cited primary-source search + a deterministic tax engine.
Work in progress (for now)
Calibre ebook library server: search, read content, curate metadata, semantic search, gated writes.
Search LinkedIn & Sales Navigator. Get structured people, companies, posts, jobs data. 4.9/5 on G2.
Stateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage
Patent search and company IP portfolio data
Realtime package holiday and charter flight prices from Sweden. Inventory not on Google Flights.
AI marketplace: search, buy, sell across Amazon, eBay, AliExpress. 13 tools.
Mercado Libre — LATAM marketplace, product search, orders, sellers, shipments
Search and fetch ~800K Federal Reserve economic time-series from the FRED API via MCP.
Search NPPES providers and resolve NUCC specialty codes via MCP over STDIO or Streamable HTTP.
Sharebench — search & pull AI skills, agents, prompts & playbooks (SKILL.md) into any MCP client
Safe personal Voila grocery automation for search, slots, cart updates, and order history
LOLBAS, GTFOBins, and process parent-child lookups for detection engineering agents.
Search, read and research the web, with hidden text stripped by default and sources hashed
POST /mcp