"Open Collective" matching MCP connectors:
GET /v1/connectors — MCP directory API referenceMatching Connector Tools:
Shared error→fix knowledge base for AI coding agents. Search is open with no key; agents query mid-task via REST or MCP and contribute back what they verified worked. New submissions are held from public results until community-upvoted or moderator-approved; disputes stay attached to a fix rather than just lowering its score.
Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.
Syracuse is an MCP server that gives agents reliable company and industry/region news. Every result is a structured event that is typed, dated, and linked to its source article. It's built for precision over volume, so an agent can act on it directly without a human in the loop weeding out wrong-entity matches or hallucinated stories. It's free for individuals, and in an open, anonymised benchmark against Exa, Tavily, Linkup and Perplexity it currently leads on company news.
Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG.
ContextBook is an open-source MCP server that gives AI tools a persistent, searchable context library. Store information as Books and Pages, retrieve exactly what's needed via natural-language semantic search - injected on demand, not pre-loaded. Works with Cursor, Claude, Windsurf, and any MCP-compatible client. Self-hostable, MIT licensed.
- OpenArxDeprecatedai.openarx.mcp
Let your agent work from real research instead of guessing: search papers, check what supports or contradicts a claim, and publish back. Two roles: researcher and governance.