MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
codebase-raggithub.com/ar-maan05/codebase-ragupdated this year
Symbol-aware, staleness-tracking RAG over a codebase, exposed over MCP; layers on rag-timetravel.
pypi MIT -
MCP server for code retrieval from a fully indexed codebase using CocoIndex
★ 16 -
java-codebase-raggithub.com/humanbean17/java-codebase-ragupdated this year
MCP server for semantic + structural search over Java codebases
pypi MIT -
codebase-rag-mcpgithub.com/sudoriaa/codebase-rag-mcpupdated this year
Local-first MCP server for hybrid codebase retrieval with Codex and ChatGPT.
MIT -
codebase-raggithub.com/di5rupt0r/codebase-ragupdated this year
Self-hosted MCP server for semantic codebase search. RAG for any MCP client (Copilot, Claude, Cline) — zero cost, self-hosted.
★ 8 -
codebase-rag-mcpgithub.com/Chri2K02/codebase-rag-mcpupdated this year
MCP server for semantic code search and Q&A — indexes any codebase using vector embeddings (OpenAI + LanceDB), exposes 4 tools to Claude Desktop, Cursor, and Copilot Chat
-
codebase-RAGgithub.com/bluewings1211/codebase-RAGupdated this year
A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing and multi-language parsing, enabling LLMs to understand and interact with code.
MIT ★ 15 -
codebase-rag-mcpgithub.com/Suyash2013/codebase-rag-mcpupdated this year
A Claude Code MCP plugin that provides token-efficient semantic codebase search. Instead of Claude burning tokens with repeated Glob/Grep/Read cycles, it hits this plugin for semantic search first and gets relevant context cheaply.
MIT -
RAG-powered codebase Q&A for multi-repo codebases, with LangChain and MCP server
npm MIT -
codebase-cartographergithub.com/Athul-n-air/codebase-cartographerupdated this year
Local, privacy-first RAG pipeline for natural-language Q&A over any codebase, using Tree-sitter parsing and an MCP server.
★ 1 -
RAG-powered codebase intelligence backend with hybrid retrieval, reranking, Pinecone, Redis/Celery, Ollama, and MCP tools.
-
RAG + MCP server + agentic code-review CLI that makes a codebase queryable by AI agents (TypeScript, Claude API, Model Context Protocol)
MIT -
smart-raggithub.com/robby031/smart-ragupdated this year
🧠 Go-based MCP server for RAG code intelligence. Index, query, and analyze your codebase using natural language.
MIT -
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
pypi MIT ★ 5,356 -
This is Retrieval augmented Generation (RAG) MCP server for a codebase built using fast api to increase contextual awareness of codebase for LLM basedcoding assistant copilots
Apache-2.0 -
CodeRAGgithub.com/maciek-O-digiaidev/CodeRAGupdated this year
Intelligent codebase context engine for AI coding agents. Semantic RAG from source code via MCP tools.
npm MIT ★ 5 -
A Rust-based Model Context Protocol (MCP) server that provides AI assistants with powerful RAG (Retrieval-Augmented Generation) capabilities for understanding massive codebases. Index codebases with FastEmbed + LanceDB, semantic code and git history searches with hybrid vector + BM25.
cargo MIT ★ 33 -
Graph RAG for private codebases — index code into a knowledge graph with semantic search and MCP server. Self-hosted, no code leaves your machine.
npm MIT -
jrag (formerly java-codebase-rag) — MCP server + jrag CLI for semantic + structural search over Java/Kotlin codebases
pypi MIT -
Code RAG MCP server: semantic indexing and retrieval of a local codebase (declaration-aware chunking + bge-m3 embeddings + Qdrant hybrid search). Exposes search_code / index_codebase / index_status / index_cancel / set_root MCP tools and a CLI, plus a loc
npm MIT -
local-rag-mcpgithub.com/overlorde/local-rag-mcpupdated this year
MCP server with local RAG pipeline — give AI agents persistent codebase search using Ollama + ChromaDB. Zero cost, zero data leakage.
★ 1 -
CodebaseRAGgithub.com/ReaperOAK/CodebaseRAGupdated this year
Local RAG over any repository via an MCP server for instant codebase querying.
-
Turn any codebase into a searchable knowledge base for AI coding assistants. Config-driven RAG pipeline + MCP server with hybrid semantic/keyword search.
NOASSERTION ★ 1 -
MCP server exposing ragd's RAG-powered codebase search
Apache-2.0 -
repo-aware-code-raggithub.com/ManavK003/repo-aware-code-ragupdated this year
AST-aware hybrid RAG over codebases with file:line citations — FastAPI + MCP. Public demo of a private live system.
MIT -
Local-first RAG for your codebase: semantically search code, GitHub PRs & issues, Jira, Slite, Slack, docs, and Claude Code sessions from the CLI or as an MCP server.
★ 1 -
ccraggithub.com/trishantpahwa/ccragupdated this year
RAG pipeline for Claude Code — indexes your codebase and exposes it as an MCP server
pypi MIT -
Semantic code index (RAG) + MCP server for codebase search
npm MIT -
Laravel-specific code intelligence: graph + vector RAG over a typed semantic graph of a Laravel codebase, exposed via MCP and CLI.
pypi Other/Proprietary License -
Tiburciogithub.com/JoaoMorais03/Tiburcioupdated this year
RAG-powered onboarding agent that indexes your codebase into a vector store and exposes MCP tools + Vue chat UI for Claude Code.
MIT -
semantic-search-mcpgithub.com/adam-hanna/semantic-search-mcpupdated this year
Give claude code RAG on your codebase
pypi MIT ★ 7 -
AI-powered codebase onboarding tool — point it at any repo and ask questions about the code. Uses tree-sitter parsing, RAG, and local LLMs.
MIT ★ 5 -
claude-lfr-mcphttps://gitlab.com/derico/claude-lfr-mcpupdated this year
Fast CPU-based RAG for codebases using BGE embeddings and Qdrant. MCP server for Claude Code.
pypi MIT -
homebrew-amanmcpgithub.com/Aman-CERP/homebrew-amanmcpupdated this year
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Claude Code and Cursor.
-
Ollqdgithub.com/leomarviegas/Ollqdupdated this year
MCP client-server RAG system — index codebases & documents into Qdrant using Ollama embeddings, with code-aware chunking and interactive chat
Apache-2.0 -
RepoMindgithub.com/akshith120/RepoMindupdated this year
An intelligent, AI-driven codebase analytics engine powered by Retrieval-Augmented Generation (RAG). It performs precise repository analysis with hybrid search. language-aware AST chunking, exact line-level citations, and MCP (Model Context Protocol) tools for seamless integration with IDEs and AI agents.
★ 1 -
A Model Context Protocol (MCP) server for semantic code search. Enables AI assistants to explore large local codebases using AST parsing and RAG.
-
repomindgithub.com/shashvat-singham/repomindupdated this year
Codebase intelligence agent — hybrid RAG (pgvector + BM25 + RRF) over any GitHub repo, agentic tool loop with cited answers, MCP server, and CI-gated retrieval evals. Next.js + Vercel.
MIT -
amanmcpgithub.com/Aman-CERP/amanmcpupdated this year
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Claude Code and Cursor.
go Apache-2.0 ★ 4 -
NervaPackgithub.com/ramdhavepreetam/nervapackno update data
Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
pypi -
seu-claudegithub.com/jardhel/seu-claudeupdated this year
Local Codebase RAG MCP Server for Claude Code - Proactive semantic indexing with AST-based chunking
MIT ★ 14 -
ultracodegithub.com/faxenoff/ultracodeupdated this year
Codebase RAG MCP server for code understanding - semantic search, duplicate detection, impact analysis for TS/JS/Python/C#/Go/Rust/Java/C++/Kotlin/Swift/Zig/Bash
npm AGPL-3.0-only OR Commercial -
Turbovec MCP Server: A local Retrieval-Augmented Generation (RAG) tool that allows AI to seamlessly read, chunk, remember, and semantically search through large project codebases.
MIT ★ 5 -
claude-lfr-mcpgithub.com/MrTango/claude-lfr-mcpupdated this year
Fast CPU-based RAG / Search for codebases using BGE embeddings and Qdrant. MCP server for Claude Code.
MIT -
@iflow-mcp/faxenoff-ultrascript-tools-mcpgithub.com/faxenoff/ultrascript-tools-mcpupdated this year
Codebase RAG MCP server for code understanding - semantic search, duplicate detection, impact analysis for TS/JS/Python/C#/Go/Rust/Java/C++/Kotlin/Swift/Zig/Bash
npm MIT -
repomindgithub.com/S-Santoshi/repomindupdated this year
Multi-agent AI system that understands a Python codebase: RAG, a Neo4j knowledge graph, and AST static analysis, behind an MCP server/client and a human-approval gate for the one write action.
-
vibecode-projectgithub.com/joejamal029/vibecode-projectupdated this year
VibeCode creates cryptographically verified Digital Twin snapshots—immutable PDFs that serialize entire codebases with full restoration. Powered by large-context LLMs, it combines multi-agent workflows (file selection, context generation, tool orchestration) with semantic RAG, security quarantine, and bidirectional MCP integration. Code as data.
Apache-2.0 -
Universal RAG Knowledge System - A shared brain for AI agents. Ingests Obsidian vaults and codebases into searchable ChromaDB with MCP + REST API interfaces.
★ 2 -
Antigravity_Optimizer_MCPgithub.com/Dimokat/Antigravity_Optimizer_MCPupdated this year
A local RAG-powered Model Context Protocol (MCP) server using Qdrant and FastEmbed to help AI coding agents navigate, understand, and optimize large codebases.
MIT ★ 3 -
contextplusgithub.com/forloopcodes/contextplusupdated this year
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.
MIT ★ 1,991 -
reporaggithub.com/davidnbr/reporagupdated this year
Fully local, zero-cost RAG knowledge layer for AI coding tools. Achieve near perfect codebase awareness with any AI tool. Supports Claude Code, Cursor, Codex, Antigravity
MIT ★ 1 -
ctx-sysgithub.com/david-franz/ctx-sysupdated this year
Local hybrid RAG over a code knowledge graph. Indexes your codebase with tree-sitter + embeddings + a relationship graph and serves precise context to any AI assistant over MCP — fusing keyword (FTS5), vector, and graph search with reciprocal rank fusion. Local-first via Ollama; works with Claude Code, Cursor, and any MCP client.
MIT ★ 15 -
Codebase Q&A with (path:line) citations — the capstone of a from-scratch AI-engineering series. Built in 8 eval-gated stages (chat → RAG → agents → hardening → production), provider-agnostic and offline-first, with 4 extensions (MCP, agent harness, context management, local models).
MIT ★ 1 -
Agent-Fusiongithub.com/krokozyab/Agent-Fusionupdated this year
Agent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documentation (Markdown, Word, PDF). Query your codebase from code agents without hallucinations. Runs 100% locally, includes a lightweight embedding model, and optional multi-agent task orchestration. Deploy with a single JAR
MIT ★ 74 -
codebase_investigatorgithub.com/DimitrisKoutselis/codebase_investigatorupdated this year
A RAG (Retrieval-Augmented Generation) chatbot that ingests GitHub repositories and lets you ask questions about the code. Built with MCP (Model Context Protocol) as a central design pattern.
-
Local-first RAG engine with hybrid search, BGE reranker, self-learning loop, and MCP server
-
codebase-memory-mcpgithub.com/vugarfamiloglu/codebase-memory-mcpupdated this year
—
-
@hyphaene/hexa-rag-mcpgithub.com/hyphaene/hexa-rag-mcpupdated this year
Semantic search MCP server for your codebase using PostgreSQL + pgvector + Ollama
npm MIT -
codebase-memorygithub.com/H-Gelender/codebase-memoryupdated this year
MCP memory server for codebase analysis: embedding-based retrieval + clean-code analysis (local-first, scalable to low-end machines).
-
Codebase Intelligence Engine & MCP Server — AST semantic chunking, tri-hybrid retrieval (BM25 + vectors + graph), and grounded LLM synthesis for any repository.
npm MIT