"The Agent Times - Publication or Newsletter" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Direct access to 60+ scraping and search tools. Extract structured data from Google (Search, Maps, Trends), Amazon, Airbnb, Social Media, and any web page directly into your AI agent.
Memwyre is an MCP-native persistent memory layer for AI agents, synchronizing context across Claude Code, Cursor, VS Code, and OpenClaw. Built with a high-precision retrieval architecture (dense vector search, BM25, and cross-encoder reranking), Memwyre achieves a benchmarked 73.1% accuracy on the Long-Context Memory (LoCoMo) benchmark. It provides secure, isolated knowledge vaults with dedicated tools (search_memwyre, save_memory, list_memories) to save and recall structured project decisions.
Search agent-ready sites or fetch one site's report; every capability probe-verified, dated.
Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.
Bounded KVP, RAG search, and wipe receipts for agent jobs over remote MCP
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.
Connect your AI to any database — PostgreSQL, MySQL, or SQL Server — in seconds.
The first low-latency wire service purpose-built for AI agents. Ingests 54+ public APIs and 71k RSS feeds across 232 countries, outputs CWF (Cognitive Wire Format) – 80% shorter than JSON, sub-second WebSocket delivery. 9 MCP tools: get_latest_signals, search_signals, get_fused_signal, scope_signals, get_facet_manifest, list_facets, get_related_signals, list_data_sources, get_billing_profile. 26 citable fusion products with verifiable formulas – no black-box scores.
Search Fragments — two tools for the queries an agent can't place, both built to decline rather than guess. resolve_fragment takes a half-remembered, cross-source query ("a musician who became famous for stopping performing") and returns a grounded answer, ranked web sources to confirm by eye, or an explicit no-resolution. verify_claim takes a specific factual assertion and returns supported, partially_supported, insufficient_evidence, or unsupported, with cited evidence and a stated_limits field that is always present. There is no confidence score — insufficient_evidence fires freely, and unsupported requires a source that explicitly contradicts, never mere absence of confirmation. Every verdict is decide-by-eye: "supported" means current web sources confirm it, not that the claim is true. Calibrated against 18 known claims before release. Free, no signup. Streamable HTTP (MCP 2025-11-25). Read-only.
Pinned, versioned sources with citable locators: search finds spans, trace reaches the bytes.
**ColdState Knowledge Search MCP Server** https://github.com/daniel-coldstate/coldstate-mcp Semantic search over 64.6M knowledge entries — the structured alternative to web search APIs and web scraping for LLM agents. No crawling, no rate limits, sub-3s responses. Cloud-hosted at services.coldstate.ai
Persistent semantic memory for AI agents: store and recall text by meaning (RAG). x402
RollCallWorks: the site's own MCP server — dataset; every answer cites the site.
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
Upkeepvo: the site's own MCP server — dataset; every answer cites the site.
Sopvo: the site's own MCP server — dataset; every answer cites the site.
Runsheetly: the site's own MCP server — dataset; every answer cites the site.
Rebadgo: the site's own MCP server — dataset; every answer cites the site.
Dispatchzo: the site's own MCP server — dataset; every answer cites the site.
Csatzo: the site's own MCP server — dataset; every answer cites the site.
