"Clever Cloud" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Source-tiered retraction and citation judgments for DOIs; abstains when evidence is thin.
Recall memories, entity profiles and source notes from your Locul cloud brain in any AI chat.
**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
Private document cloud for MCP agents. Claim a link, then store and recall.
graphrag-ts is a TypeScript GraphRAG engine over PostgreSQL/pgvector, served as a Streamable HTTP MCP endpoint. The public read tier answers without credentials, rate limited to 20 requests per minute per IP: integrity_paper_status (retraction status and paper identity), retraction_propagation (whether a retraction propagates to a paper) and integrity_evidence_audit (evidence-path audit with source tiers). A bearer API key unlocks the full GraphRAG tool set: hybrid vector/keyword graph query, corpus-wide map-reduce answers, index jobs and memory writes.
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.
Persistent memory for AI assistants: store, search, and connect knowledge across conversations.
Recall authorized Vault notes with keyword and hybrid search, original excerpts, and source paths.
Search screen text, audio transcriptions, app data and memories already synced to your Screenpipe account. Offers synced-devices and search-synced-content with read-only OAuth (data-sync:read). Requires Data Sync to be available and enabled. Local-only recordings are excluded; connecting does not enable uploads. Requested results go to your connected AI provider. Submitted by the Screenpipe team.
Team-synced persistent AI agents memory for Claude, Codex, Cursor, claude.ai, chatgpt.com... that is always current.
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.
Graph memory for AI agents: entities, cause-effect links, cross-session recall, time travel.
Cloud-hosted MCP server for secure AI access to enterprise data sources via CData Connect AI.
NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments
