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. Lore Context ★ 4
    Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
  2. Dense Knowledge ★ 1
    Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.
  3. Toon Memory ★ 11
    Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
  4. io.github.LuizEduPP/rememb ★ 4
    Persistent memory for AI agents — local JSON, zero config, no server required.
  5. io.github.LuuOW/meridian-skills
    Routes AI tasks to dynamic LLM-generated skills via an orbital classifier.
  6. io.github.Lyellr88/marm-mcp-server ★ 354
    Universal MCP Server with advanced AI memory capabilities and semantic search.
  7. io.github.Lykhoyda/ask-claude ★ 17
    Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions
  8. io.github.Lykhoyda/ask-llm ★ 17
    Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
  9. io.github.Lykhoyda/ask-ollama ★ 17
    Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
  10. io.github.MGM-FALCON/quelllm-mcp
    MCP server for quelllm.fr: 190+ open-weights LLM catalog - list, compare, VRAM and cost estimates
  11. OpenClaw Consensus
    9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.
  12. ComfyUI Builder ★ 3
    ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.
  13. Pipe (SPR) MCP Server ★ 2
    AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.
  14. Pipe Docs (SPR) MCP Server ★ 2
    Docs + source RAG for Pipe language: semantic search, cited answers, code symbol lookup.
  15. io.github.MagneticDogSon/fixflow
    Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.
  16. fish-bridge — Session Knowledge Graph ★ 2
    Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
  17. io.github.MarcelRoozekrans/memorylens-mcp ★ 10
    MCP server for .NET memory profiling — in-process heap snapshots via EventPipe with leak heuristics
  18. io.github.MarcellM01/tinysearch ★ 226
    Self-hosted web research for MCP agents.
  19. MarsNMe ★ 7
    Agent-agnostic memory backend that preserves continuity between humans and AI over time.
  20. io.github.MastadoonPrime/agent-memory
    Persistent, agent-owned memory with encrypted storage and shared knowledge commons.
  21. Yagami AI Context Firewall ★ 1
    Govern model, retrieval, memory, and tool access for AI applications and agents.
  22. io.github.MauriceIsrael/SmartMemory ★ 3
    Neuro-symbolic memory for LLMs (POC)
  23. Compartment ★ 586
    Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
  24. io.github.MemoriLabs/memori-mcp ★ 2
    Memori MCP server — persistent AI memory with recall and augmentation tools
  25. Memphora ★ 3
    Add persistent memory to AI assistants. Store and recall info across conversations.
  26. PraisonAI ★ 9,051
    AI Agents Framework with Self Reflection and MCP support
  27. io.github.MetriLLM/metrillm ★ 7
    Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
  28. io.github.Mibayy/token-savior ★ 1,154
    Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.
  29. io.github.Mibayy/token-savior-recall ★ 1,154
    Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.
  30. io.github.Michael-WhiteCapData/ollama-handoff ★ 3
    Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
  31. MidOS - MCP Community Library ★ 8
    Curated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP
  32. MidOS - MCP Community Library ★ 8
    Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
  33. Memory Vault ★ 62
    Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
  34. io.github.Mikerichardmail/clarik-mcp-server ★ 1
    Clarity and memory persistent workspace context manager for Claude.
  35. MCP Gateway ★ 60
    Universal MCP gateway with Meta-MCP discovery, routing, and REST API capabilities.
  36. temporal-mcp ★ 3
    Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.
  37. ChangePacket
    Web and MCP change memory with native diff UI; later calls return only what changed.
  38. GHOSBC Safety Gate
    Agent governance with A2A/Shopify/MCP trust audits, action screening, and decision UI.
  39. NodeRooms Discovery
    Read-only NodeRooms Agent discovery, safety policy, public indexes, and arrival contract.
  40. io.github.MkTurner74/botverse ★ 1
    Transcode/conform/splice video, convert docs, transcribe audio for AI agents. Free $1 trial.
  41. Mnemosyne OS ★ 13
    Memory the human governs, on their own machine, plus what other coding agents here wrote.
  42. Modellix Agent Canvas
    Local MCP canvas for Modellix image generation, editing, task recovery, and visual project work.
  43. CommitLore ★ 9
    Git-native decision memory for coding agents: only the decisions still in force for the edited path
  44. MemoCat — Shared AI Memory ★ 39
    One shared, persistent memory across AI agents and systems, with semantic recall and live updates.
  45. io.github.Morous-Dev/engram-cc ★ 1
    Universal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.
  46. io.github.MukundaKatta/agentcast ★ 1
    Structured-output enforcer: extract and validate JSON from messy LLM text.
  47. io.github.MukundaKatta/agentvet ★ 1
    Validate tool-call args before execution. Returns LLM-friendly retry hints.
  48. io.github.MukundaKatta/citecite-mcp
    Inject, parse, and strip [N] citation markers in RAG outputs.
  49. io.github.MukundaKatta/promptbudget-mcp
    Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
  50. io.github.MukundaKatta/ragdrift-mcp
    Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.