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.
- RE-call MCP Memory Server ★ 3
Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing. - io.github.Goldentrii/agent-recall ★ 371
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only. - io.github.GoneTone/mcp-server-taiwan-weather ★ 11
用於取得臺灣中央氣象署 API 資料的 Model Context Protocol (MCP) Server - Lex
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy. - io.github.HBarefoot/engram ★ 7
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud. - io.github.HUANGCHIHHUNGLeo/claude-real-video ★ 2,135
Let any LLM watch a video locally — and search everything it has ever watched. - RAGScore ★ 15
Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM. - io.github.Hafeok/product-cli ★ 6
Knowledge graph CLI for managing features, ADRs, and test criteria as MCP-discoverable artifacts. - io.github.HarimxChoi/google-surf-mcp ★ 291
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links. - io.github.HaseebKhalid1507/velocirag ★ 11
Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search. - Crystallize MCP
Crystallize headless commerce tools for AI agents via Model Context Protocol - marocain.investments — {GIN} real-estate intelligence (Morocco) ★ 1
{GIN} verdict, M-Value AVM, market facts + semantic search for Moroccan real estate. Moat-safe. - io.github.Hiroshi-Ichiyanagi/kagami
Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM. - io.github.Hushlor/mcp-server-tauri
A Model Context Protocol server for use with Tauri v2 applications - io.github.Hustada/collective-memory
MCP server for persistent, semantic memory across AI sessions - io.github.IPv6/mcp-transcribe ★ 8
MCP-Transcribe server allows LLMs to interact with the text content of audio/video files - MCP Memory Gateway ★ 26
Pre-action gates that block AI agents from repeating known mistakes. - io.github.Ikalus1988/misakanet ★ 491
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text. - io.github.Indhar01/memograph ★ 4
Graph-based memory system for LLMs with knowledge graphs and semantic search. - Contextful ★ 4
Efficient context management: code search, evidence packs, and memory for coding agents. - io.github.Inflectra/mcp-server-spira
A Model Context Protocol (MCP) server enabling AI assistants to interact with Spira by Inflectra. - io.github.IntelagentStudios/mcp-file-processor
Text extraction, keyword extraction, language detection, and chunking for RAG - io.github.Intina47/context-sync ★ 192
Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more - Persome ★ 1,320
Local-first personal memory and model server for trusted MCP agents on macOS. - io.github.IsaiahDupree/agentsearch-mcp
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG. - io.github.JKHeadley/moltbridge ★ 5
Agent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity. - io.github.Jason26214/omni-computer-use ★ 3
Windows MCP server replicating Anthropic's computer-use tool surface, for any MCP client. - IA-QA — 130+ QA & Dev Tools for AI Agents
130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free. - io.github.JesusGarcia9009/lethe
Context GC for LLM agents: offload large tool outputs and recall them to save tokens. - io.github.JimothySnicket/gemini-image ★ 1
Google Gemini image generation, editing, and local processing via MCP - io.github.JoaoBerne/cli-bridge-mcp ★ 2
Other AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys. - io.github.JubaKitiashvili/context-mem ★ 18
Persistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools - Junê ★ 1
Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions - io.github.KIOKO-LAB/freshvault
Local semantic search over your Obsidian vault - always fresh, never reindex. - io.github.KSym04/limpet ★ 2
Persistent engineering memory for AI coding agents. Survives refactors, knows when it is stale. - UNBLOCK
UNBLOCK org-brain — shared memory and comms for human + agent teams. By Kaeva Labs. - io.github.KairosMobius/memory-nexus-mcp
Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs. - io.github.KairosMobius/nexus-memory-mcp
Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs. - io.github.Kastalien-Research/thoughtbox ★ 64
Extended reasoning with structured processes, persistence, and workflow guidance - io.github.KlossKarl/loom
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval. - AccordTrace
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST. - AgentLore
AI-verified knowledge base with trust scoring, temporal facts, and skill cards. - Acta — Verifiable Agent Memory
Verifiable agent memory with signed ledger receipts — verify every write offline. - io.github.Kzino/vorim-mcp-server ★ 73
AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI - LLM Pulse
AI visibility analytics for brand mentions, citations, sentiment, and GEO reports - Frenchie
OCR, transcription, file extraction, and image generation for AI agents via MCP. - Copilot Memory MCP ★ 4
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required. - Refinery MCP
Clean raw HTML into LLM-ready text before agents spend tokens. - io.github.LeandroPG19/cuba-memorys ★ 27
Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph. - UltraMemory ★ 1
One memory, every AI: Claude, ChatGPT, Perplexity, Gemini, Cursor, OpenClaw, Hermes, any MCP client.