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.
- io.github.Vorim-AI-Labs/vorim-mcp-server ★ 73
AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI - emem, the verifiable memory protocol for the physical world ★ 56
Shared memory for AI agents. One address per fact, one signature you check. No key to read. - io.github.VouchlyAI/pincer ★ 6
Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture - Freshdesk
MCP server for Freshdesk — tickets, contacts, companies, agents, groups, and knowledge base. - io.github.Wenyveo/escrow
Agent-to-agent escrow on Robinhood Chain. Post quests with ETH/USDG bounties and settle on-chain. - WhichModel
Cost-optimized LLM model routing recommendations for autonomous AI agents - knowmind
Knowledge graph & long-term memory for AI agents: recall, relations, store, stats, health. - CrowTerminal - External Brain for AI Agents
External Brain for AI Agents - persistent versioned memory for creators - io.github.Wolfe-Jam/gemini-faf-mcp ★ 2
Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format. - lean-memory ★ 47
Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud. - Longhand ★ 13
Local memory for Claude Code. Semantic recall across session history with zero API calls. - io.github.XJTLUmedia/context-first-mcp ★ 1
37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline. - io.github.XXO47OXX/spa-reader-mcp ★ 1
MCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content - Open Computer Use ★ 121
Give any LLM its own computer — Docker sandboxes with bash, browser, docs, and sub-agents - io.github.Yarmoluk/ckg-mcp
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native. - io.github.Yarmoluk/ckg-nemotron-perplexity
NVIDIA Nemotron + Perplexity Sonar as knowledge graphs — 2 domains, 83 nodes. MCP-native. - NVIDIA AI CKG
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native. - NVIDIA NemoClaw CKG
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native. - io.github.YogiAdhik/civicrm-mcp
Model Context Protocol server for CiviCRM — AuthX-first, schema-introspected, write-gated. - io.github.YonasValentin/mcp-memory-graph ★ 1
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token. - io.github.Yveshby27/brick-bacnet-mcp ★ 1
Read-only BACnet/IP MCP gateway with Brick + Haystack semantic tagging at ingest - io.github.ZahiriNatZuke/local-delegate ★ 5
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota. - Whisper Transcribe
Transcribe audio locally with faster-whisper or through the OpenAI Whisper API. - ChatCrystal ★ 58
Local-first AI PKM memory for coding conversations. - io.github.ZentricProtocol/zentric-protocol-mcp
Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms. - TSUNG AI Research & Analysis
Multi-LLM AI Research & Analysis — smart routing, consensus analysis, due diligence reports - io.github.aayoawoyemi/ori-memory ★ 323
Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. - io.github.abahocodes/llmgraph
Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools. - Cortex
Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first. - io.github.abe238/hotin ★ 3
What's hot in AI right now, ranked with receipts from GitHub, HN, npm and Hugging Face. - Promptheus ★ 17
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends) - io.github.abhinavala/context-cloud
Persistent AI memory with shared team workspaces, typed knowledge chunks, and cross-tool support. - io.github.abhishek2432001/deeprepo
Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search. - DELPHI Oracle ★ 1
Real-time AI intelligence signals and temporal knowledge graph for agent economy - FastMCP server for surgical queries against a vault knowledge graph (NetworkX no ★ 2
FastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).… - io.github.adelinamart/robrain ★ 81
Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach. - io.github.agenerationforwordz-tech/strata ★ 6
Self-hosted AI memory server. Persistent memory on your hardware, not the cloud. - io.github.agenson-horrowitz/agent-output-guard
Validate and verify data from other agents before acting on it. Zero LLM costs. - Agentic Reputation Gateway
Read-only gateway for durable agent identity, consent, recognized work, and signed receipts. - Lore ★ 8
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction. - Lumen ★ 86
Self-hostable agentic-AI LMS: catalog, RAG tutor, FSRS reviews, AI authoring, ingest. - defluff ★ 1
Deterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés. - BrainBrainBrains
Persistent memory + context layer for AI dev teams. 17 tools via MCP. - io.github.aiconsulting06000-tech/acf-mcp
Official ACF® MCP server — Agentic Commerce Framework® governance copilot for AI assistants. - aide-memory ★ 2
Persistent memory layer for AI coding agents — your agent remembers what you taught it. - io.github.aimsise/color-engine-mcp
Six pure, in-memory CSS color tools: parse, convert, WCAG/APCA contrast, gamut map, ramps, solver - Airweave Search ★ 6,565
MCP server for searching Airweave collections with natural language queries. - io.github.ajc3xc/meridian
Persistent memory, task coordination, and HITL queue for AI coding sessions. - io.github.akomyagin/aimcpgate
MCP gateway/proxy: multiplexes tool calls across upstream MCP servers into one catalog. - io.github.alanzha2/observe-instrument-mcp
Add OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.