Best Knowledge AI Skills & MCP Servers
133 curated Knowledge skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Codemap
Local-first persistent codebase memory for MCP-enabled coding agents.
Youtrack
MCP server for comprehensive YouTrack integration: issues, work items with reports, user activity search, knowledge base, projects and users
Code Graph Rca
RCA infrastructure for AI-built code. Code knowledge graph + opinionated RCA engine, exposed via MCP (Cursor / Claude Code / Cody / Cline / Continue / Windsurf / Zed) plus CLI and library. RCA is the wedge; the same engine covers code review, refactor bla
Mergemind
MergeMind MCP server — read-only доступ к общей памяти команды агентов (markdown vault с гибридным поиском BM25 + vector + rerank). Запускается через `npx -y @agfpd/mergemind-mcp@latest` из .mcp.json плагина MergeMind (gh-репо agfpd/MergeMind).
Server
MCP server for SharedMemory — persistent AI memory for any tool
Bc Code Intelligence
BC Code Intelligence MCP Server - Complete Specialist Bundle with AI-driven expert consultation, seamless handoffs, and context-preserving workflows
Vibe Hnindex
MCP server for indexing and searching codebases with keyword + semantic search. Works with Claude, Cursor, Windsurf, Antigravity.
Codegraph
Live, queryable knowledge graph for your codebase. Indexes JS/TS into an embedded graph DB with embeddings and exposes an MCP server Claude Code and Cursor can call.
Neurodivergent Memory
A Model Context Protocol server for knowledge graphs designed around neurodivergent thinking patterns
Cli
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
Unerr
Local-first code intelligence CLI for unerr
Gitnexus
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
Wyrm
🐉 Wyrm — the memory layer that makes AI assistants remember, learn from failures, execute long-running goals, and federate across every session. MCP server with 126 tools across persistent memory, counter-pattern blocking, OODA agent loop, knowledge grap
Confused Ai
Fast TypeScript AI agent framework — per-request agents, 30+ model providers, 100+ integrations, 20+ vector DBs, 10+ databases, sessions, memory, knowledge, tracing, evals, HITL, teams, and workflows.
Spandrel
Turn markdown file trees into navigable, queryable knowledge graphs served via REST and MCP
Server
Framework-agnostic domain knowledge API for Brainerce. Provides SDK docs, types, business flows, critical rules, and store capabilities to AI tools like Lovable, Cursor, Bolt, v0, and Claude Code. Does NOT provide framework-specific boilerplate — clients
Hsa
HSA - Hierarchical Semantic Analysis MCP Server for AI Code Agents. Token-optimized context engine with BM25+ search, Merkle tree change detection, 84+ built-in library docs, persistent memory, and real-time dashboard.
Affine
Model Context Protocol server for AFFiNE - enables AI assistants to interact with AFFiNE workspaces, documents, and collaboration features.
Agent Knowledge
Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
Mediawiki
Model Context Protocol (MCP) server for MediaWiki
Kobsidian
TypeScript MCP server for Obsidian with a filesystem-first LLM Wiki layer, Dataview / Canvas / Kanban / Mermaid / Marp / Templates tools, and both stdio and Streamable HTTP transports.
Server Memory
MCP server for enabling memory for Claude through a knowledge graph
Obsidian
MCP server for AI assistants to interact with Obsidian vaults
Synapse Cortex
Powerful, self-contained AI context layer. Combines persistent memory, temporal knowledge graph, and hybrid code search into one local engine. Zero cloud, 100% private.
About Knowledge skills on iClaude
iClaude is the universal install layer for AI skills. Every Knowledge 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.