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.
-
iflow-mcp_ferparra_graph-rag-mcp-servergithub.com/yourusername/graph-rag-mcp-serverupdated this year
Graph RAG MCP Server for Obsidian vault with unified ChromaDB store and Gemini 2.5 Flash
pypi MIT -
A Model Context Protocol (MCP) server implementation for graph-based memory storage with RAG capabilities
-
jqassistant-graph-raggithub.com/2015xli/jqassistant-graph-ragupdated this year
Source code graph RAG (graphRAG) for Java/Kotlin development based on jQAssistant
Apache-2.0 ★ 13 -
Multi-agent LiteRAG MCP server for advanced code graph analysis
npm MIT -
Advanced Graph RAG MCP Server with sophisticated graph structures, operators, and agentic capabilities for AI agents
npm 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 -
🔌 Exposes RAG + Knowledge Graph over MCP — hybrid retrieval with vector embeddings + graph traversal. Citation-aware. MIT.
pypi MIT -
hybrid-graph-raggithub.com/tahasiddiquii/hybrid-graph-ragupdated this year
Hybrid (BM25+dense+RRF) and graph multi-hop retrieval with a labeled benchmark (recall@k/MRR/nDCG) and an MCP connector. Fully offline, zero API keys.
MIT -
AndyAI Knowledge Factory with ASAL: structural awareness, repo graph, AST pipeline, MCP graph tools, hybrid RAG+Graph routing and evidence-backed impact maps.
MIT -
rag-anythink-mcpgithub.com/serkanyasr/rag-anythink-mcpupdated this year
Model Context Protocol server for advanced RAG with Knowledge Graphs
MIT ★ 6 -
mcp-win-stdio-ragactive
Windows-optimized RAG MCP Server with Playwright crawling, Link Graph trees, and local hybrid search.
pypi MIT -
Self-hosted agentic RAG for multi-repo code intelligence: real ASTs (Roslyn/TSC/Pyright) → semantic knowledge graph (SQLite + sqlite-vec) → SGC graph convolution → REST + embedded MCP server. Local embeddings, zero external APIs.
★ 1 -
rag-memory-pg-mcpgithub.com/kshidenko/rag-memory-pg-mcpupdated this year
PostgreSQL-based RAG Memory MCP Server with Supabase - hybrid semantic search + knowledge graph
npm -
rho-graphgithub.com/rhofield/rho-graphupdated this year
Graph-RAG code indexer for AI agents — token-efficient code search via MCP tools backed by Neo4j
npm MIT -
KnowLP-RAG: dual knowledge-graph RAG for Markdown notes — dsh plugin add @eqman00003/knowlp-rag · MCP + native Cordis plugin for DeepSeek Harness (dsh) & Claude Code
npm MIT ★ 3 -
TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.
Apache-2.0 ★ 31 -
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.
MIT ★ 20 -
knowledge-graphgithub.com/agent-engineering-studio/knowledge-graphupdated this year
Companion repo del libro 'AI che Ragiona' (G. Zileni, 2026) — Knowledge Graph production-ready con Graph-RAG ibrido, server MCP e agenti AI in Python, Neo4j, Redis e Microsoft Agent Framework.
-
AP-RAG (Academic Paper Retrieval-Augmented Generation): citation-backed retrieval over scientific papers, for people and for AI agents. Web and desktop apps, an MCP server and a CLI, over a LightRAG knowledge graph.
-
Advanced Graph RAG MCP Server with file location identification, graph processing, and result summarization capabilities
npm MIT -
Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).
npm MIT -
Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes, a search layer for a Karpathy-style LLM Wiki. Wikilinks are the graph, SQLite the only store.
pypi MIT ★ 15 -
The Karpathy LLM Wiki, production-ready. Zero-RAG personal knowledge base with MCP server, multi-agent support, knowledge graph visualization, and hallucination enforcement. No embeddings, no vector DBs — just markdown + git.
★ 5 -
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 -
GraphRAGgithub.com/MvdB/GraphRAGupdated this year
Graph-based RAG system: markdown files → PostgreSQL+AGE graph → MCP server
MIT -
grimoiregithub.com/mosszxc/grimoireupdated this year
Multi-project Knowledge Base — Graph RAG with GPU transcription, vector search, MCP server
MIT -
codeatlas-mcp-serverupdated this year
CodeAtlas MCP - an enterprise-grade local-first Code Graph RAG MCP Server.
pypi Apache-2.0 -
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 -
Quant-Agent-OS: open-source quantitative intelligence platform for AI clients (MCP, SDK). Quant Research (Graph RAG with cited evidence) and Quant App Factory. Pre-alpha.
NOASSERTION -
MCP server for code intelligence: AST code graph in Memgraph + dual RAG + BM25 search
MIT -
MCP server for EdgeQuake Graph-RAG — use EdgeQuake as persistent agent memory
npm Apache-2.0 -
@edgequake/mcp-servergithub.com/raphaelmansuy/edgequakeupdated this year
MCP server for EdgeQuake Graph-RAG — use EdgeQuake as persistent agent memory
npm Apache-2.0 -
Cortex-agents_infragithub.com/kth3/Cortex-agents_infraupdated this year
The High-Performance, Hardware-Adaptive Knowledge Engine for MCP Agents: Hybrid Graph-RAG & Atomic Concurrency Control.
MIT ★ 2 -
Self-hosted SDLC context graph + RAG over GitLab & GitHub repos: code graph (definitions, imports), MR diffs, CI, planning, security — served to AI agents via MCP. A free, lightweight OSS alternative to GitLab Orbit (Qdrant + NATS; no ClickHouse/K8s).
MIT -
amnisgithub.com/mandoof1/amnisupdated this year
☀️ Persistent Memory + RAG + Wiki Compilation for AI Agents — MCP server + Web UI with interactive knowledge graph
MIT ★ 1 -
lightrag-mcpgithub.com/nailmailster/lightrag-mcpupdated this year
MCP server for LightRAG API — 30 tools for knowledge graph RAG
MIT -
Zero-dependency, offline-first Graph-RAG memory system for AI agents — hybrid semantic+keyword+graph search, multi-agent task queue, MCP server, Obsidian-native vault.
npm MIT ★ 1 -
Neuro-Symbolic Law-to-AST Compiler, Microsoft Z3 Formal Verifier, 12-MCP Suite, Contextual+Graph RAG, and Autonomous PR Enforcer (JusticeSphere AI / ComplianceOS)
MIT ★ 3 -
graphmindgithub.com/arthurmgraf/graphmindupdated this year
Autonomous Knowledge Agent Platform - Agentic RAG with Knowledge Graphs, hybrid retrieval, LangGraph agents, and MCP server
MIT ★ 1 -
Persistent memory for AI agents over MCP: knowledge graph, vectors and graph RAG on your own hardware. Install a node, connect Claude Code or another agent, use the seven memory tools.
pypi Apache-2.0 ★ 1 -
knowledge-mastergithub.com/subzone/knowledge-masterupdated this year
Local-first knowledge graph for developers. Graph-native RAG with MCP server, blast radius analysis, convention enforcement. Your AI agent's permanent memory.
MIT ★ 3 -
knowledge-reduce-coregithub.com/nelslindahlx/knowledge-reduce-coreupdated this year
High-performance Knowledge-RAG pipeline featuring self-correcting LLM critique loops, MLX fine-tuning, real-time watcher daemons, pluggable local KùzuDB/cloud Neo4j graph stores, and an interactive 3D WebGL dashboard.
NOASSERTION -
Documentation RAG for coding agents: vector search, knowledge graph, agent memory, and an MCP server — torch-free local embeddings via fastembed
pypi Apache-2.0 ★ 1 -
ragmcpgithub.com/gashel01/ragmcpupdated this year
Production RAG for AI agents — reranking, SPLADE, ColPali, knowledge graph. Python lib · CLI · MCP server · FastAPI.
pypi Apache-2.0 ★ 1 -
BrainAIgithub.com/BrezhnevEugen/BrainAIupdated this year
Native macOS personal knowledge base with AI — LightRAG knowledge graph, RAG chat, SpriteKit graph viewer, MCP bridge, 6 LLM providers. Privacy-first: your data stays local.
Apache-2.0 ★ 4 -
Friday AI MCP server — expose Friday code intelligence, Graph RAG, coding plan and MR tools to Cursor / Claude Code / Codex via Model Context Protocol
npm MIT -
Make Obsidian the Local Brain for AI Agents. Embedded MCP Server (HTTP/SSE) with Graph-RAG for WorkBuddy, Cursor & Claude Desktop.
MIT ★ 1 -
a knowledge-graph and RAG system that extracts requirements into neo4j, queryable through an ollama and MCP chat client with RL tuned retrieval strategies.
-
ragPapergithub.com/i1ight/ragPaperupdated this year
Local-first paper RAG + read-only MCP server: hybrid/reranker retrieval, self-correcting DOI enrichment, and citation graphs over your Zotero/PDF library — queryable from Claude Code, Codex, or any LLM.
MIT ★ 2 -
Built an agent using LangChain, Hybrid RAG, SurrealDB memory, and GitHub MCP tools, Django, capable of answering repository-specific questions through vector search, graph retrieval, and live GitHub metadata. Exposed the agent as an MCP server for A2A communication with any external AI agents through a standardized MCP client.
-
ckg-mcpgithub.com/yarmoluk/ckg-mcpupdated this year
Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.
pypi MIT -
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
MIT ★ 613 -
AI assistant that combines document retrieval (RAG) and knowledge graph search with LangGraph orchestration, Google Gemini, and a separate MCP server for actions. Includes a terminal chat interface and automated tests.
-
Graph-Augmented Code Intelligence RAG engine pairing deterministic AST call graphs with dense vector search to boost direct-callee Recall@8 from 0.0% to 53.3% (+53.3 pp) under a 5.8ms p95 latency bound. Powered by a QLoRA fine-tuned Qwen2.5 adapter (70.02 CodeBLEU), quality verification harness, and production Model Context Protocol (MCP) server.
MIT -
knowledge-gungithub.com/akaddo97/knowledge-gunupdated this year
Generate paste-ready chatbot context bundles from a curated knowledge graph. Topic-scoped two-hop neighbourhood walker + hand-written intros. No vector RAG, no embedding cost, pure markdown. Pair with knowledge-gun-mcp to call from any MCP-aware LLM client.
MIT -
Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.
MIT ★ 3 -
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.
-
llamaindex_pydantic_raggithub.com/yagosamu/llamaindex_pydantic_ragupdated this year
Multi-source RAG (LlamaIndex + Pydantic) that routes questions across SQL, vector, and graph stores - exposed via FastAPI and MCP.
-
A universal, MCP-first RAG platform with pluggable components for vector stores, knowledge graphs, and data sources. Designed for production use with hybrid retrieval (RRF), cross-encoder reranking, and grounded generation.
-
MCP server combining Qdrant vector search, Neo4j knowledge graphs, and Crawl4AI web intelligence with agentic RAG capabilities. FastMCP 2.0 architecture with enterprise security, monitoring, and Kubernetes deployment. AI/ML engineering powerhouse.
MIT ★ 9