Back to the catalog

MCP servers · AI, RAG & memory

50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

  1. IBM watsonx.ai Granite ★ 142
    IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.
  2. three.ws Marketplace ★ 142
    Browse and discover the public three.ws agent marketplace and skills catalog. Read-only.
  3. MCP Registry Monitor ★ 28
    Monitor MCP registry for new servers - Discord Slack notifications alerts
  4. Metaplex Agent Registry ★ 142
    Deploy AI agents on-chain on Solana with an EIP-8004 identity. Deploy fee funds $THREE buybacks.
  5. three.ws Avatars & Agents ★ 142
    3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws.
  6. AI Tool Discovery Agent ★ 30
    AI agent discovers MCP servers from GitHub npm - analyzes APIs configs
  7. CoderSwap MCP Server
    Build searchable AI research knowledge bases with hybrid vector search directly in Claude Desktop.
  8. io.github.nk3750/jitapi ★ 7
    Turn any OpenAPI spec into an executable agent interface using graphs and semantic search.
  9. io.github.nmxmxh/pronto-stream
    Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
  10. kg ★ 9
    Local knowledge graph memory MCP server for AI assistants.
  11. io.github.noahgift/pmcp
    High-quality Rust SDK for Model Context Protocol (MCP) with full TypeScript SDK compatibility
  12. Local FAISS MCP Server ★ 33
    Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
  13. Distillery ★ 24
    Knowledge base for Claude Code with semantic search, feed intelligence, and teams
  14. Novyx MCP
    Persistent memory for AI agents with rollback, audit trails, and semantic search.
  15. io.github.nrwl/nx-console ★ 1,414
    A Model Context Protocol server implementation for Nx
  16. io.github.nrwl/nx-mcp ★ 1,414
    A Model Context Protocol server implementation for Nx
  17. Purl
    Search and save to your Purl read-it-later knowledge base from any MCP client.
  18. io.github.nugehs/aiglare ★ 1
    Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.
  19. THOR ★ 4
    Local memory for coding agents. A rule with a runnable proof can refuse a wrong command.
  20. Forge Orchestrator ★ 159
    Multi-tool AI orchestration: Claude Code, Codex, Gemini on shared repos. 11 MCP tools, stdio.
  21. RelayShield Security Intelligence
    Breach, SIM swap, infostealer, domain lookalikes, MCP registry risk, prompt-injection detection.
  22. io.github.octoryn/octopus-blackboard ★ 7
    Shared memory & coordination for AI coding agents — a blackboard, not an orchestrator.
  23. io.github.ohad6k/ditto ★ 290
    Mine your local AI coding session logs into a profile your agent loads before every task.
  24. io.github.ohad6k/emulo ★ 290
    Mine your local AI coding session logs into a profile your agent loads before every task.
  25. sqz
    Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
  26. Myrmex Hive ★ 2
    Zero-inbound-port MCP gateway for managing distributed edge servers over reverse SSH tunnels
  27. PMB AI ★ 279
    Local-first persistent memory for AI coding agents.
  28. io.github.omarkeshk/council-ai
    Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
  29. io.github.omega-memory/core ★ 218
    Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
  30. OMEGA Memory ★ 218
    Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
  31. io.github.oneprofile-dev/curatedmcp-catalog-mcp
    Search the CuratedMCP catalog of risk-classified MCP servers and check verification status.
  32. io.github.onetrueclaude-creator/mcp-knowledge-gaps
    Find what your knowledge base mentions but doesn't actually explain.
  33. Ratary Memory MCP ★ 1
    Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context.
  34. io.github.oomkapwn/enquire-mcp ★ 33
    Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.
  35. io.github.ooples/token-optimizer-mcp ★ 522
    Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.
  36. OpenMetadata ★ 15,185
    Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
  37. io.github.opencontext-team/mcp-server
    An MCP server that provides visual memory and context storage with knowledge graph capabilities
  38. io.github.openfused/openfuse-mcp ★ 18
    Encrypted mail, shared memory, and persistent context for AI agents.
  39. io.github.openpoem/spec-score-mcp ★ 2
    Score your specs before feeding them to an LLM. MCP server with radar chart visualization.
  40. MCP Registry Validator — Check Endpoints Actually Resolve
    Check an MCP endpoint resolves: liveness, live tool list, schema drift. Free.
  41. Anamnesis
    Cross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git
  42. Keito
    Track Keito time entries and LLM costs from AI agents.
  43. agentmem ★ 4
    Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
  44. AgentNet ★ 1
    Agent-to-agent referral network. Discover, recommend, and refer users between AI agents via MCP.
  45. Global Agent Memory ★ 14
    Shared, project-aware memory for Claude Code, Codex, and other agents with human review.
  46. io.github.paiml/pmcp ★ 53
    High-quality Rust SDK for Model Context Protocol (MCP) with full TypeScript SDK compatibility
  47. Datawrapper ★ 50
    A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants
  48. Palveron Governance Gateway
    Advisory governance checks for MCP hosts; enforcement runs in the Palveron remote MCP proxy.
  49. io.github.pamela-0/boot-doctor-mcp ★ 1
    Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.
  50. Panella
    Governed, self-hosted memory for AI agents: writes queue until a named person approves.