Best Knowledge Graph AI Skills & MCP Servers
37 curated Knowledge Graph skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Knowledge Keeper
AI Memory & Knowledge Management MCP Server — 32 tools, BM25 R@5=95%, hybrid search (RRF), knowledge graph, analytics, cloud sync, Obsidian compatible. Works with Claude Code, Cursor, Gemini CLI, Windsurf, hermes-agent.
Superlocalmemory
Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.
Unerr
Local-first code intelligence CLI for unerr
Open Zk Kb
Shared, persistent memory for AI assistants, built on the Zettelkasten method.
Flywheel Memory
MCP tools that search, write, and auto-link your Obsidian vault — and learn from your edits.
Server
MIND MCP Server — 28 tools. The most complete AI memory layer with the Focus → Project → Outcome → Task hierarchy (mind_focuses + extended mind_life with item_type/parent_id/focus_id and cross-account project sharing via share/list_shares/revoke_share), d
Stifler Memex
Developer context continuity system — temporal knowledge graph for AI coding agents via MCP. Inspired by Vannevar Bush's 1945 concept of a machine that remembers everything.
Nex
Nex CLI provides organizational context & memory to AI agents. Connect email, CRM, Slack, meetings, and 100+ tools into one knowledge graph. Delegates to the nex-cli binary.
Bhived
Bhived MCP Server — shared knowledge graph for AI agents. Query, write, and inspect collective AI knowledge through the Model Context Protocol.
Lightrag
Model Context Protocol (MCP) server for LightRAG - 30 fully working tools with complete RAG and Knowledge Graph integration
Ori Memory
Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.
Hermit Graph
Persistent memory for AI coding agents. Knowledge graph with 4-tier taxonomy, confidence scoring, and MCP protocol support for Claude Code, Cursor, Gemini CLI, Windsurf, Cline, Codex, and OpenCode.
Brain
Personal Knowledge Brain for developers — MCP server with typed neurons, hybrid search (FTS5 + vector), knowledge graph, vault encryption, time-travel history, and spaced repetition. 100% local, SQLite-based.
Alaya
Alaya MCP Server — a memory engine for AI agents that remembers, forgets, and learns
Mcp
Verifiable Memory-as-a-Service for AI Agents — MCP server with local SQLite or cloud mode
Mcp
DEPRECATED — install the Claude Code plugin at gramatr/claude-plugin instead. This npm package no longer ships a CLI; Codex and Gemini integrations are paused pending HTTPS+OAuth MCP support.
Gitnexus
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
Mcp
MCP server for Neruva -- reliability infrastructure for production AI agents. One install, agent stops forgetting / drifting / repeating mistakes, every failure replayable bit-for-bit. v0.27 ships the qbound KG engine: 47.5% EM on MemoryAgentBench CR-MH (
Obsidian Brain
Standalone Node MCP server: semantic search + knowledge graph + vault editing for Obsidian, no plugin required.
Dare Cli
DARE Framework - CLI, GraphRAG engine, MCP server and shared types in a single package
Cosmos
MCP server for the Polarity exocortex. Read and write your personal knowledge graph from any LLM client.
Memesh
MeMesh — Local memory for Claude Code and MCP coding agents. One SQLite file, zero cloud required.
Mcp
Standalone MCP server for Copass — drop-in discover/interpret/search + Context Window tools for any MCP client (Claude Agent SDK, Claude Code, Claude Desktop, Cursor)
Fabric
Fabric MCP server — code intelligence, governance rules, and cloud-sync disaster recovery over a local codebase index
About Knowledge Graph skills on iClaude
iClaude is the universal install layer for AI skills. Every Knowledge Graph skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.