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. 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.
-
agentic-codebasegithub.com/agentralabs/agentic-codebaseupdated this year
Semantic code intelligence for AI agents — compile repositories into navigable concept graphs with impact analysis, coupling detection, and prophecy.
pypi MIT ★ 21 -
A multi-agent AI system that audits any codebase and generates a styled health report (PDF). Built with LangGraph, MCP, and Gemini — three specialized agents scan structure, review code, and write the report.
★ 1 -
A sub-harness (both an MCP server and an MCP client). Delegates documentation and source code analysis, as well as interactions with related context-providing MCP servers, to a local or inexpensive OpenAI-compatible LLM. Drastically reduces token usage and context size for coding agents on the top-tier LLM.
Apache-2.0 ★ 3 -
Stacklit: AI Codebase Indexing 2026 – Zero-Setup Local Repo Mapping for Agents
★ 1 -
🎯 Intelligent React codebase consultant that detects design system drift and guides AI coding agents via CLI and MCP
MIT -
codebase-dnaupdated this year
Codebase intelligence layer for AI coding agents - auto-discovers conventions, architecture, and static contract signals via MCP
npm MIT -
RAG + MCP server + agentic code-review CLI that makes a codebase queryable by AI agents (TypeScript, Claude API, Model Context Protocol)
MIT -
Long-term codebase memory for AI coding agents: module map, entry points, and notes, served over CLI and MCP.
npm MIT -
codebase-memory-plusgithub.com/InM1nd/codebase-memory-plusupdated this year
MCP server + local dashboard for visual codebase summaries, dependency graphs, and cross-tool AI agent config management (Claude Code, Cursor, Codex)
-
Offline, read-only MCP server that gives AI agents a precise picture of a local codebase. Python implementation with AST-level symbol extraction and real .gitignore support.
MIT -
MCP server for semantic codebase navigation: AST symbol index, LSP-backed references/definitions, and semantic refactoring tools for AI coding agents.
MIT -
Local, offline codebase context for AI coding agents: feature slices across UI, API and data layers, flow tracing, impact and test selection, diff review and a permission map, over MCP or CLI
npm MIT -
Static codebase analysis as MCP tools — give AI coding agents a map of your repo (import graph, API routes, frontend-to-backend edges) instead of burning tokens rediscovering it
MIT -
An MCP server that gives AI agents a cited, searchable memory of a codebase: hybrid search, git history, impact analysis and doc-drift detection. Local and free.
pypi MIT -
AST-driven Neo4j knowledge graph of your codebase, exposed to Claude Code via MCP. Map your monorepo once; let the agent query it instead of re-reading files.
npm MIT -
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
npm NOASSERTION ★ 68 -
codebase-analyzer-mcpgithub.com/jaykaycodes/codebase-analyzer-mcpupdated this year
Multi-layer codebase analysis with Gemini AI. 4 agents, 5 commands, 3 skills for architecture analysis, pattern detection, and dataflow tracing
npm MIT ★ 3 -
@froredion/codebase-indexeractive
MCP server that indexes your working codebase into Codebase Indexer and gives your coding agent semantic search over it.
npm UNLICENSED -
mcp-codebasegithub.com/DmitriyOT/mcp-codebaseupdated this year
MCP server for semantic codebase navigation: AST index of symbols, imports and dependencies for AI agents (TS/JS, C#)
MIT -
ddev-codebase-memory-mcpgithub.com/IT-Cru/ddev-codebase-memory-mcpupdated this year
Codebase knowledge graph for your project in DDEV — MCP server for AI coding agents, plus a browsable graph UI.
Apache-2.0 ★ 1 -
CLI-first TypeScript codebase analysis with hotspots, impact, dead-export detection, and architecture metrics. Includes optional MCP server for AI agents.
npm MIT ★ 8 -
codebase-mcpgithub.com/Dipanshu-js/codebase-mcpupdated this year
Auto-generate AI-ready context from your codebase. One command → CONTEXT.md ready to paste into Claude, Cursor, ChatGPT or any MCP agent. Full MCP server mode included.
npm MIT ★ 2 -
codemap-mcpgithub.com/ayoubachour/codemapupdated this year
Local-first persistent codebase memory for MCP-enabled coding agents.
npm MIT -
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 Q&A: ask questions about a Python/JS repo, get answers with validated citations. Async FastAPI + Postgres/pgvector, AST and tree-sitter chunking, hybrid retrieval + RRF, MCP tool, LangGraph agent with human review, Langfuse tracing, 40-question eval harness, CI.
-
Index codebases for AI agents with one command. Build a local map of your repository without server requirements or setup.
-
codegraph-mcpgithub.com/strcoder4007/codegraph-mcpupdated this year
Understand any codebase in seconds - MCP server for AI coding agents
-
orgraph-mcpgithub.com/tss-pranavkumar/orgraphupdated this year
Codebase knowledge graph MCP server — call chains, topology, and hybrid search for coding agents
pypi MIT -
@cidx/cliupdated this year
Codebase indexer and MCP server for AI coding agents
npm -
Cursor-style AST Codebase Indexing & Surgical Slicing MCP Server for AI Coding Agents
MIT ★ 1 -
Persistent codebase memory for AI coding agents. MCP server + CLI + dashboard.
npm MIT ★ 4 -
The Private Context Layer & Super Brain for Your Codebase. Give AI agents persistent memory, deep dependency graphs, and instant code context
npm MIT ★ 26 -
Self-learning AST context engine & knowledge graph optimized for Laravel codebases and AI coding agents
npm MIT -
Persistent memory service & codebase knowledge graph for AI coding agents (Slim TypeScript Edition)
npm MIT -
ariadne-mcpgithub.com/madan2248c/ariadneupdated this year
MCP server that gives coding agents a structural map of a codebase
npm MIT -
Dual-Layer Codebase Knowledge Graph & Episodic Memory Engine for AI Coding Agents
npm MIT -
archmapgithub.com/matiasxth/archmapupdated this year
Architecture-as-Code for AI Agents. Scan your codebase, generate machine-readable architecture maps.
npm MIT -
vibeguard-mcpupdated this year
MCP server that helps AI coding agents understand codebases before making changes — summarize_project, find_related_files, pre_edit_check
npm MIT -
Shows what your coding agent is doing on Fiada's map of your codebase: a tool hook and an MCP server for Claude Code, Cursor and Codex.
npm MIT -
Stop making your AI re-read your codebase. Stacklit maps your repo once and keeps the map fresh. In a 450-session test, agents ran 82% fewer grep and glob searches. Free, MIT, one Go binary. Sets up Claude Code, Cursor, Codex and 22 more.
go MIT ★ 131 -
meshmindgithub.com/AntoniovanDijck/meshmindupdated this year
A single MCP server merging local codebase mapping, recency research, and token compression for AI agents.
MIT ★ 1 -
pi-shazamgithub.com/gjczone/pi-shazamupdated this year
Pi coding agent native codebase awareness toolkit — 7 structural analysis tools. Also supports MCP (Cursor, Claude Desktop, Windsurf, etc.)
npm MIT -
merlin-mcpgithub.com/anthropics/merlinupdated this year
Merlin MCP Server - AI-powered codebase intelligence for coding agents
npm MIT -
Local repository code search and codebase memory for Codex, Claude Code, and MCP coding agents
pypi -
@pushkarshetye9867/accionkggithub.com/pushkar803/accionkgupdated this year
Graph-powered code intelligence for AI agents. Scan any codebase, query via MCP or CLI.
npm UNLICENSED -
@xuansang2770/gitnexusgithub.com/sang2770/gitnexusupdated this year
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
npm PolyForm-Noncommercial-1.0.0 -
Give coding agents trustworthy, cited answers about your codebase. Code graph + MCP server, no LLM required.
pypi MIT ★ 9 -
Local-first codebase intelligence memory and task context for coding agents, via CLI, MCP, and local HTTP.
pypi Apache-2.0 ★ 1 -
EverMindgithub.com/YPYT1/EverMindupdated this year
An integrated local-first memory system for AI coding agents with MCP, skills, reviewed notes, and codebase graph memory.
AGPL-3.0 -
probe-codegithub.com/matiasxth/probeupdated this year
Codebase intelligence for AI agents. Index your code at function-level, query what matters, know what breaks.
npm MIT -
@iflow-mcp/abhigyanpatwari-gitnexusgithub.com/abhigyanpatwari/gitnexusupdated this year
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
npm PolyForm-Noncommercial-1.0.0 -
@ryogrid/gtags-mcpgithub.com/ryogrid/gtags-mcpupdated this year
MCP server that wraps GNU GLOBAL(gtags) for AI coding agents to analyze codebases
npm MIT -
Local memory, a codebase index, and working discipline for AI coding agents. Zero dependencies, no network, MCP included. Measured, not asserted.
MIT -
Codebase analysis MCP server for AI agents: complexity metrics, size thresholds, prop drilling, and code smell detection built on tree-sitter and tokei.
npm MIT ★ 1 -
Local codebase maps and change impact analysis for humans and AI agents, with an MCP server.
NOASSERTION -
The Persistent Intelligence Layer for Codebases - Local-first CLI & MCP server for AI agents
npm MIT -
semantic-grepgithub.com/datnguyenzzz/semantic-grepupdated this year
Make multiple codebases available as context for any coding agent without spending too many resources or sacrificing quality
MIT -
Live architecture signal map for agentic coding. Tree-sitter + MCP bridge lets agents query, trace, and animate your codebase graph in real time.
MIT ★ 2 -
Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.
npm MIT ★ 2 -
A fact base and lenses for any codebase. Zero-LLM-cost indexing, MCP server for coding agents, BYOK.
MIT