MCP servers
122 017 serveurs issus du registre officiel, de GitHub et de npm. Filtrez par catégorie, transport et langage.
122 017 serveurs issus du registre officiel, de GitHub et de npm. Filtrez par catégorie, transport et langage.
Collez son dépôt GitHub et nous l'ajouterons après une révision rapide.
Soumettre un serveurLocal code intelligence engine — three-tier FAISS + SQLite index with 10 MCP tools for semantic code search, blast radius analysis, and architectural investigation
Codebase intelligence layer — an embedded knowledge graph that makes call-graph and change-impact analysis instant.
MCP server giving coding agents semantic + structural search over your codebase, so they reuse proven patterns instead of guessing. Finalist - Cursor × Superteam Georgia Hackathon 2026.
AST-aware hybrid RAG over codebases with file:line citations — FastAPI + MCP. Public demo of a private live system.
Map every feature and user flow in a codebase from git history and code structure. No Jira, no annotations. Bug hotspots, health scores, symbol-level attribution and an MCP server for AI coding agents.
A Python AST Model Context Protocol (MCP) server for codebase architecture inspection, symbol search, import dependency mapping, and docstring coverage auditing.
Local memory, a codebase index, and working discipline for AI coding agents. Zero dependencies, no network, MCP included. Measured, not asserted.
Multi-repo cross-codebase API migration impact mapper & codemod (Greptile)
Provider-neutral, validated contracts for typed Python callables : deterministic JSON Schema, strict decoding, exact binding, and sync/async invocation. I have made it for LLM's that maintain large codebases, click the U
Codebase architectural invariant assertion sentinel (Codex Astra)
Start querying your codebase's intent
An AI detective for your codebase. Uses LangChain and MCP to hunt down bugs in your Git history and prove exactly what broke.
Multi-file AST dependency graph parser & minimum context slicer extracting symbol call-trees for coding agents.
AST-level static call-graph analyzer and dead code pruner identifying orphaned functions, unreachable methods, and token-bloat clusters.
Local codebase maps and change impact analysis for humans and AI agents, with an MCP server.
A Python-based GitHub MCP Server that enables AI assistants to interact with GitHub repositories, manage issues, explore codebases, and perform developer workflows through the Model Context Protocol (MCP).
The ultimate MCP server for code intelligence. Smart context, semantic search, call graphs, pattern detection & token optimization. Makes LLMs understand any codebase perfectly.
MCP client-server RAG system — index codebases & documents into Qdrant using Ollama embeddings, with code-aware chunking and interactive chat
One command. Your codebase, AI-ready.
An integrated local-first memory system for AI coding agents with MCP, skills, reviewed notes, and codebase graph memory.