Context7

Knowledge Graph Memory

Official

Build and query persistent semantic networks for data management. A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

Provides a knowledge graph-enhanced retrieval system that combines vector search with graph-based relationships for persistent memory and contextual information retrieval

T

Think Tool

Remote

Provides a structured thought process management system for maintaining explicit reasoning steps, policy verification, and tool output analysis through persistent memory storage

Maintains persistent project context through a structured Memory Bank system of five markdown files that track goals, status, progress, decisions, and patterns with automatic timestamp tracking and workflow guidance for consistent documentation across development sessions.

TypeScript-based server for tracking project context across sessions, enabling persistent knowledge sharing through modular, markdown-based memory management with support for multiple development modes.

Structures reasoning processes through defined thought stages, managing a history of thoughts with metadata for transparent, step-by-step problem solving and decision making.

Provides persistent intelligence infrastructure for codebase analysis through hybrid Rust-TypeScript architecture that combines Tree-sitter AST parsing with semantic concept extraction, developer pattern recognition, and SQLite-based persistence to build contextual understanding of codebases over time, learning from developer behavior and architectural decisions.

Basic Memory

Official

Knowledge management system that builds a persistent semantic graph in markdown, locally.

Provides structured problem-solving tools through Sequential Story and Sequential Thinking approaches, enabling narrative-based or Python-implemented thought sequences with branching and visual formatting capabilities for enhanced memory retention.

Database-backed project memory management system that stores decisions, progress tracking, and system patterns in a queryable knowledge graph with vector embeddings for semantic search and comprehensive import/export functionality.

Exa Search

Official

Empower AI assistants like Claude with real-time web data using the Exa MCP Server. This Model Context Protocol server connects AI models to the Exa AI Search API, enabling safe, up-to-date web searches across diverse tools such as academic papers, company data, LinkedIn, Wikipedia, GitHub, and more. Its flexible toolset enhances research, competitor analysis, and content extraction, providing comprehensive information for smarter AI interactions. Designed for seamless integration with Claude Desktop, the Exa MCP Server boosts AI capabilities by delivering fast, reliable, and controlled access to the latest online information.

DeepWiki

Official Remote

Instantly turn any Deepwiki article into clean, structured Markdown you can use anywhere. Deepwiki MCP Server safely crawls deepwiki.com pages, removes clutter like ads and navigation, rewrites links for Markdown, and offers fast performance with customizable output formats. Choose a single document or organize content by page, and easily extract documentation or guides for any supported library. It’s designed for secure, high-speed conversion and clear, easy-to-read results—making documentation and learning seamless.

Docfork

Official Remote

Retrieves up-to-date documentation and code examples for any software library through the Docfork API, automatically selecting relevant libraries and providing topic-focused documentation with configurable response size limits.

Nia

Official

Nia is an MCP server that provides additional context to coding agents. It improved Cursor’s performance by 27% by indexing extra documentation and codebases that coding agents can't.

G

Grep

Official Remote

Issue search queries and retrieve code snippets from GitHub that match specific patterns or regular expressions, filtered by language, repository, and file path.

Deepcon

Official

Deepcon is a powerful MCP (Model Context Protocol) server that provides AI agents with intelligent access to package documentation. Instead of searching the web or relying on outdated training data, your AI coding agents can search through up-to-date documentation using semantic search.

Rtfmbro

Official Remote

Stay ahead with instantly up-to-date, version-specific docs for any package. rtfmbro is an MCP server that delivers precise, real-time documentation from GitHub at the exact version your project uses. It supports popular ecosystems like Python and Node.js, features smart caching, full context extraction, and tight integration with coding agents. AI assistants can access READMEs, documentation trees, and search repositories, ensuring coding help is always accurate and current. Perfect for developers or AI tools needing the right docs, right when you need them—without stale data or version mismatches.

GitMCP

Official Remote

Stop vibe-hallucinating and start vibe-coding—GitMCP empowers your AI assistant with instant, up-to-date documentation and code from any GitHub project. This free, open-source server eliminates code hallucinations, providing reliable API usage, accurate code examples, and effective support for even new or niche libraries. With smart search tools and a privacy-first approach, GitMCP helps AIs deliver trustworthy answers by pulling information straight from the source. Enjoy enhanced productivity with lightning-fast access to the latest content, all while keeping your projects secure and your workflow smooth.

Ref Tools

Official

Supercharge your AI coding agent with focused, efficient access to documentation. Ref MCP empowers LLM tools to search and extract only the most relevant technical content from APIs, libraries, and services, reducing token usage and avoiding information overload. Smart filtering and precise page reading help your agent find just what it needs, making code generation and research faster, cheaper, and more accurate. Designed to support evolving agent workflows, Ref MCP ensures your AI always has up-to-date documentation context without unnecessary noise or cost, optimizing both performance and productivity for modern AI-powered development.