"Researching an author based on their books" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
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 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.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Know whether an AI agent should REUSE or REFETCH a URL before retrieving it again.
A high-performance, edge-native Data Refinery Engine built on Cloudflare's serverless AI stack (Workers, Workers AI, D1, KV, Vectorize) designed to continuously ingest unstructured data, refine it into pristine machine-readable structured intelligence, compute semantic diffs, and serve it directly to AI agents via the Model Context Protocol (MCP) and REST APIs.
Market data and web intelligence for AI agents, paid per call in USDC on Base via x402.
The world's first named AI prompt quality score. Score, optimize, and compare LLM prompts before they hit any model. Free tier available. Built on PEEM, RAGAS, G-Eval, and MT-Bench frameworks. x402-native on Base.
Multilingual YouTube → Knowledge Pack engine. Paste a video URL and get a structured pack — summary, key ideas, glossary, quiz, transcript with timestamps — in Spanish, Portuguese, German, or English. Anonymous endpoint plus OAuth-gated tools for library search, RAG Q&A on a single pack, and Anki export.
LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
Marketplace where AI agents buy and sell books — curated domain knowledge that improves tasks.
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.
Real-time web search with answer-ready results for Claude, Cursor and any MCP client. A Tavily alternative: same speed, 20.2% fewer tokens, higher answer quality (60.7% of decided duels won) on a public benchmark. Hosted on mcp.serpdive.com or npx serpdive-mcp.
The only News based AI MCP your agents will ever need — custom categories, global regions, and time-scoped results in one tool. We use multi-vector & sparse-hybrid search to search through thousands of articles across the world to find the exact news you're looking for.
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Persistent cloud memory for Ai coding assistants. 33 MCP tools, 85% accuracy on LoCoMo benchmark. Semantic search, auto-skills, knowledge graph, quantum-safe encryption. Works with Claude Code, Cursor, Windsurf, and any MCP client.
Explainable graph-retrieval memory engine with an RL-trained management policy.
LLMtoMD is the memory layer for AI coding agents. It converts any document — PDF, DOCX, slides, spreadsheets, images, audio, even whole websites — into clean, structured Markdown, then exposes it over MCP so your agent can search your FRDs, specs, and API docs on demand instead of re-reading (or forgetting) them.
MCP memory server with shared team workspaces, typed knowledge chunks (decision, finding, convention, state, question, reference), role-based access, and cross-tool support for Claude, Cursor, and Codex. The only MCP memory server built for engineering teams. Features automatic deduplication, two-layer retrieval (LLM KB selection + hybrid vector/BM25/RRF fusion), a web dashboard with knowledge graph visualization, and attribution tracking. Zero server-side LLM costs.
Exam-scored knowledge brains your agent searches over MCP, plus a public list of their gaps.
Your office's procedures inside Claude or ChatGPT - verified citations or an honest refusal.
