"smart" matching MCP servers:

Enables token-efficient structural code exploration using tree-sitter AST parsing, with tools for symbol search, outlines, source unfolding, call graphs, and related-file discovery.

Enables secure execution of JavaScript and Python code in cloud-based E2B sandboxes with integrated file management capabilities, allowing Claude to run and test code safely in isolated environments.

A single MCP server that fronts many downstream MCP servers and Skills, exposing only four tools (search, call_tool, use_skill, admin) so that an agent's context window only ever sees search results on demand.

A global framework for creating reusable command shortcuts and slash commands that work across any directory. It enables systematic code refactoring, debugging, and auditing through a hierarchical configuration system with global defaults and project-specific overrides.

Connects AI assistants like Claude to PHP's XDebug debugger for runtime inspection, breakpoint control, and variable tracking, enabling natural language debugging of PHP applications.

Intelligent AI routing and integration platform for seamless provider switching

Provides intelligent semantic code search using local AI embeddings, enabling natural language queries to find relevant code by meaning rather than exact keywords. Indexes codebases in the background with smart project detection and privacy-first local processing.

Provides 14 enhanced intelligent search tools for both international platforms (GitHub, StackOverflow, NPM, etc.) and Chinese platforms (CSDN, Juejin, WeChat docs, etc.). Each tool includes smart URL generation, search tips, and related suggestions for comprehensive technical research.

Enables AI assistants to perform intelligent semantic code search across codebases using local AI embeddings for meaning-based retrieval.

MCP server that reduces AI agent token usage by up to 90% through intelligent context compression. Enables efficient code exploration, multi-file refactoring, and debugging by providing tools for smart reading, searching, and managing code context.

Reduces token consumption for AI coding agents by 50-70% through intelligent code context filtering, Git delta tracking, and local SQLite/Tree-sitter indexing.

Enables AI assistants to search codebases by meaning using local semantic embeddings, and provides tools for package version lookup, reindexing, cache clearing, workspace switching, and server status.

Enables AI agents to safely work on Windows developer workstations through governed, project-scoped filesystem access, durable command execution, bounded search, Windows operations, and resource-aware runtime controls. It also supports optional developer-context backends for code navigation, repository graph exploration, and memory retrieval.

Smart Tree MCP cuts storage by up to 95% using quantum-context compression — not just files, but full project histories. Track, compress, and version smarter with zero-bloat ops across Git, FS, and memory.

Enables AI coding assistants to search codebases by meaning using local AI embeddings, with tools for indexing, cache management, workspace switching, status checks, and package version lookup. It supports incremental and progressive indexing with configurable embedding dimensions to find relevant code even when terminology differs.

Enables comprehensive code analysis including quality assessment, security vulnerability detection, refactoring suggestions, complexity calculations, and automatic documentation generation for multiple programming languages.

Enables mapping Figma designs to a project's own component library — shadcn/ui, antd, mui, or Astryx — by resolving variants against authoritative component contracts instead of guessing. It compiles Figma nodes into code and then deterministically writes the resulting files into the codebase, cleaning node-id artifacts and updating exports.

A stateful MCP server that provides persistent memory, deterministic static analysis, and evolving conventions for AI coding assistants.

An enhanced MCP server that fetches prompts from GitHub repositories with intelligent discovery, composition, and management features.

An enhanced MCP server that fetches prompts from GitHub repositories with intelligent discovery, composition, and management features.