"Resources for improving coding skills and debugging code" matching MCP servers:

LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.

Enables MCP hosts to discover, browse, and load Agent Skills from one or many SKILL.md libraries over the Model Context Protocol, with namespaced libraries, search/list/get tools, progressive disclosure, and a digest-verified pull client for syncing skills to disk.

Serves any directory of Agent Skills (SKILL.md folders) over MCP, exposing skills/list, skills/get, and skill:// resources so clients can enumerate and retrieve each skill's frontmatter and files. Every returned file comes with a real SHA-256 digest, letting clients verify content rather than merely trust it.

Enables Claude to request and receive skills from a database on demand, allowing agents to fetch step-by-step instructions for tasks like lead research while keeping user credentials and execution on the user's own machine.

Enables AI clients to discover, search, retrieve, and read supporting files from a centrally published, versioned skill registry through four read-only MCP tools.

Enables semantic search over codebases using natural language queries, returning relevant code snippets with source locations. Integrates with Claude Code for automatic codebase exploration.

An MCP server that provides dynamic codebase context to Claude Code through tools like hybrid search, recent changes, and symbol definitions, enhancing AI-assisted coding with local RAG.

Enables AI coding assistants to semantically search codebases by meaning rather than exact text, with zero external daemons and fully local embeddings. Works out-of-the-box with Claude Code, Gemini CLI, Antigravity, and Cursor.

An installable MCP server that reviews diffs/PRs against a target repository's own coding conventions, learned via RAG over its code, docs, and lint config, citing specific file:line sources.

Enables hybrid retrieval over interpretable Gemini documentation knowledge graphs through eight MCP tools, combining vector, keyword, and graph-boosted search with deprecation filtering.

Enables semantic code search across indexed codebases using natural language queries, with support for CLI and MCP interfaces.

Enables semantic code search across indexed code folders using vector embeddings, with support for multiple embedding providers and automatic file watching. Provides an admin UI and integrates with MCP clients for natural language code queries.

A remote MCP server that exposes a library of Claude-style SKILL.md packages, enabling Claude to search, retrieve skills, and read supporting files via MCP tools.

Multi-provider embedding MCP server with local Milvus for semantic code search. Works with Claude Code, Cursor, Windsurf, and other MCP-compatible IDEs.

Remote MCP server for Claude that exposes a library of SKILL.md packages, enabling listing, searching, and retrieving skill instructions and supporting files for use in conversations.

Enables Claude to intelligently analyze and query codebases using knowledge graphs, supporting natural language code search, relationship discovery, and incremental updates.

Enables intelligent discovery and management of Claude Skills through semantic search, ratings, favorites, and community curation. Provides tools to search, upload, rate, and organize skills with natural language queries and comprehensive metadata.

A semantic code search MCP server that enables natural language queries against your codebase, supporting features like related file discovery and context expansion, all running locally.

A pipeline that segments source code into chunks, generates embeddings, and stores them in ChromaDB. It provides semantic context to AI coding assistants via the Model Context Protocol.

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.