Design contract layer for AI agents. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth so every agent gets the same authoritative design rules before it builds. Local-first.
Rabbithole provides an infinite canvas for learning by allowing users to open documents, select text, ask questions, and receive answers that open as child documents, all running locally via an MCP server.
Connects Claude Desktop to a RAGBrain knowledge base to enable semantic search, document retrieval, and namespace management. It allows users to browse collections, discover documents by topic, and access full text content through natural language.
Educational MCP server with 17 tools for mathematical calculations, matrix operations, statistical analysis, and data visualization. Includes persistent workspace, cloud hosting, and safety features like restricted eval.
An MCP server that provides persistent memory for AI assistants by automatically recording and injecting project-specific rules, decisions, and configurations through session hooks. It utilizes Gemini to analyze conversations, manage token-efficient context, and perform autonomous background tasks like documentation updates.
Provides long-term memory capabilities for MCP clients by wrapping the Mem0 API, enabling semantic search, storage, retrieval, and management of conversation memories across users and agents.
An MCP server implementation that helps Claude remember and learn from programming errors by storing, retrieving, and finding similar errors with full context.
An MCP server that enables interaction with Markdown knowledge bases, allowing users to search and retrieve content by tags, text, URL, or date range from their local markdown files.
A structure-aware MCP server for querying the SPOKE biomedical knowledge graph, enabling entity resolution, schema introspection, path finding, and safe Cypher queries for biomedical knowledge inference.
CLI and stdio MCP server for noticed. Exposes ~50 noticed agent capabilities (network search across GitHub + LinkedIn, missions, PRM, memory, workspace, web search, cron, ...) via two meta-tools — search + execute — to any MCP-aware client (Claude Code, Claude Desktop, Cursor, ChatGPT).
Enables AI assistants to act as apprentices that learn from users through the apprentice effect and spaced repetition, helping users solidify knowledge by teaching.