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.
-
Local-first engineering knowledge retrieval with deterministic ingestion, provenance, hybrid search, reproducible evaluation, CLI, and read-only MCP.
MIT -
fusionpactgithub.com/fusionpacttech/fusionpact-vectordbupdated this year
The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, built-in RAG, MCP server, multi-agent orchestration, and agent memory architecture.
npm Apache-2.0 -
A local-first, open-source knowledge engine for document ingestion, retrieval, grounded synthesis, citations, and MCP.
-
Ghana's Information Retrieval Engine & Model Context Protocol (MCP) server for local web, government, academic, and legal search.
MIT -
Context engineering toolkit for AI agents. 24 MCP tools across retrieval, memory, context, and team telemetry. .NET 10. No cloud deps.
nuget MIT ★ 2 -
Your AI. Your Memory. — persistent memory engine for AI agents: typed memories with provenance, hybrid retrieval, reversible lifecycle, MCP/DeepSeek Harness plugin, SDK/CLI/REST.
MIT -
🧠 Deterministic, LLM-free context engine and MCP server for coding agents — compact retrieval, project memory, optional routing, and secure secret isolation.
MIT -
contextweaver-mcpgithub.com/wchiway/contextweaver-mcpupdated this year
Semantic code retrieval engine for AI coding agents, with hybrid search, AST-aware chunking, graph expansion, and token-aware context packing.
npm MIT ★ 2 -
Fault-tolerant RAG engine with hybrid retrieval, durable ingestion, grounded answers, observability, and MCP.
-
Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.
★ 48 -
Local-first code-retrieval engine for AI agents: AST-aware chunking, hybrid BM25/vector search, MCP server, CLI, VS Code extension. MIT
npm MIT -
books_raggithub.com/zcoderz/books_ragupdated this year
Precision-first RAG engine for technical books — hybrid retrieval, reranking, citation-backed answers with abstention, 34 MCP tools
Apache-2.0 ★ 1 -
Agentic RAG and GraphRAG context engineering: hybrid retrieval, temporal knowledge graph, community search, reranking, token budgeting and groundedness-gated answers, with MCP and A2A
Apache-2.0 -
riffluxgithub.com/yxbh/riffluxupdated this year
Local/offline hybrid retrieval engine for markdown and files: SQLite FTS5/BM25 + local embeddings + RRF + MCP tools.
MIT -
Long-term memory engine for coding agents: two-stage retrieval + gating, hybrid BM25+vector, Ebbinghaus decay, single SQLite file, MCP-ready. Dogfooded daily: 3,300+ memories across 4.5 months.
MIT ★ 6 -
Local-first, code-aware engineering cognition for AI coding agents - persistent memory, contextual retrieval, and continuous cognition about your codebase.
oci MIT ★ 3 -
Task-adaptive repository context engine for coding agents: local MCP, exact token budgets, and dependency-aware retrieval.
MIT ★ 1 -
Cruxgithub.com/CueCrux/Cruxactive
Retrieval engine with cryptographic receipts. Token-budgeted search, fact store, gap reporting. Single binary, runs anywhere.
npm Apache-2.0 ★ 2 -
Persistent memory and context-engineering platform for AI agents with memory intelligence, hybrid retrieval, token-budgeted context compilation, custom LLM APIs, MCP, evaluation, observability, and a React control plane.
-
protocontextgithub.com/protocontext/protocontextupdated this year
Deterministic knowledge layer for RAG systems. Open standard + search engine + semantic retrieval for AI-readable web content.
Apache-2.0 ★ 2 -
crawlforgegithub.com/makaren-pro/crawlforgeupdated this year
Local-first web-context engine for AI agents with async crawling, BM25 retrieval, token-budgeted context, and MCP.
MIT -
Context engineering platform for AI coding agents with graph-aware retrieval, repository intelligence, MCP integration, and evaluation.
-
ai-docs-vector-db-hybrid-scrapergithub.com/BjornMelin/ai-docs-vector-db-hybrid-scraperupdated this year
Retrieval-augmented docs ingestion stack: Firecrawl + Crawl4AI + Qdrant vector search with FastAPI and MCP interfaces for AI engineers.
MIT ★ 11 -
A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.
Apache-2.0 ★ 16 -
fusionpact-vectordbgithub.com/FusionpactTech/fusionpact-vectordbupdated this year
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
npm Apache-2.0 -
airflow_sec_raggithub.com/kartikeyamandhar/airflow_sec_ragupdated this year
Grounded answer engine over SEC filings: span-cited, refusal-gated answers with XBRL numbers, hybrid retrieval, a golden-set deploy gate, Airflow orchestration, and an MCP tool surface.
-
cognitive-project-layergithub.com/kharkilirov1/cognitive-project-layerupdated this year
Local-first context engine for coding agents: project skeleton, symbols, references, graph, retrieval, confidence, MCP, CLI, and HTTP API.
NOASSERTION ★ 5 -
Local-first MCP server for RAG over engineering documentation (GOST/SP, project PDF/DOCX/XLSX, IFC/DWG). Lemonade embeddings + LanceDB hybrid search with query planning and retrieval-quality filtering.
MIT -
loregithub.com/candyhunterz/loreupdated this year
Context Engine with self-improving memory over a code corpus. RAG-shaped but built for 2026 long-context models: dumb high-recall retrieval, four-channel merge (BM25 + ripgrep + symbol + vector), OpenAI + MCP server surfaces.
MIT -
Portable hybrid (BM25 + dense + RRF) retrieval engine and a label-free evaluation harness — extracted from a personal AI-assistant memory index and decoupled to run on any source tree.
pypi MIT ★ 4 -
Collector-first engineering evidence backend for deterministic ingestion, Qdrant retrieval, cited investigation, readiness reports, workflows, evals, and Core MCP. Azure deployment scaffold; not yet production-grade.
★ 1 -
OreoLook — an open-source, OpenAI-compatible agentic web search and deep-research engine with streaming, MCP tools, Redis memory, Qdrant retrieval, and PDF exports.
CC0-1.0 ★ 24 -
Local-first Governed Memory Engine for Codex, Antigravity & DSH (DeepSeek Harness). Conclusion-first progressive retrieval, automatic tool-error follow-up, compaction survival, counterexample circuit-breakers & native visual UI.
MIT ★ 1 -
motion-site-buildergithub.com/olbboy/motion-site-builderupdated this year
A retrieval-driven engine + 17-rule linter that plans, builds, and grades motion UI across five design languages — 92 prompts, 8 MCP tools, 3 agent skills. Motion that looks designed, not generated.
MIT ★ 4 -
essencegithub.com/ruchit-p/essenceupdated this year
Rust web retrieval engine for LLM-ready markdown, RAG pipelines, and MCP agents.
MIT ★ 6 -
Python SDK + MCP server for Telys — embedded, on-device memory & retrieval for AI assistants. 19-tool MCP surface (io.github.thyn-ai/telys on the Official MCP Registry); the engine is a separate closed, signed on-device runtime — the SDK and MCP surface are Apache-2.0.
pypi Apache-2.0 -
CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg: facts from any source, human-ratified. Recommended engines: Graphiti (server), LadybugDB (embedded).
npm MIT ★ 17 -
Autonomous SDR knowledge engine - campaign architecture, retrieval-first playbooks, MCP email dispatch.
MIT -
MCP-powered offensive security intelligence engine using local semantic retrieval, FAISS, and RAG. Local-first MCP server for authorized offensive security research, detection engineering, and education. Authorized use only.
-
Ragebot-MCPgithub.com/atharvrahate296/Ragebot-MCPupdated this year
Intelligent Project Context Retrieval Engine for AI assisted development environments. Leverages local as well as cloud LLM support using project indexing and smart querying.
pypi -
Islamic texts (Hadith & Tafsir) hybrid retrieval engine and Model Context Protocol (MCP) server combining ChromaDB semantic search and SQLite FTS5
-
Personal knowledge engine: Neo4j graph + Qdrant vectors, hybrid retrieval with provenance, tool-using agents and an MCP server.
MIT -
conduitgithub.com/naumanAhmed3/conduitupdated this year
An MCP (Model Context Protocol) server exposing a pgvector hybrid-retrieval engine as tools, resources and prompts over Streamable HTTP.
-
lucidmemgithub.com/libr3andr3/lucidmemupdated this year
Memory engine for AI agents: per-project isolation enforced in Postgres, explainable hybrid retrieval, and an MCP connector
MIT -
The Compiler-Aware Operating System Kernel CodeGraph Engine for Token-Efficient Structural Codebase Retrieval
MIT ★ 4 -
@paradigm-memory/memory-coregithub.com/infinition/paradigm-memoryupdated this year
Local-first cognitive map retrieval engine. SQLite + FTS5 + pluggable embeddings, with audited mutations and an offline consolidator.
npm Apache-2.0 -
RAG-Based-Movie-Selector-With-Gilhari-And-ORMCPgithub.com/HarshitBansal9/RAG-Based-Movie-Selector-With-Gilhari-And-ORMCPupdated this year
A RAG-based movie recommendation engine using ChromaDB for semantic search and an ORMCP/Gilhari backend for structured data retrieval.
★ 1 -
Offline-first EU4 modding knowledge engine with structured retrieval, local vanilla/mod indexing, scope-aware diagnostics, CLI, Python API, and optional MCP tooling.
MIT -
Persistent memory engine for AI coding agents — preserve project context, retrieve relevant knowledge, and maintain consistency across sessions using MCP.
MIT ★ 6 -
reconstructgithub.com/Kenotic-Labs/reconstructupdated this year
The continuity layer for AI systems. DTCM engine + MCP server + REST API. Store from Claude, retrieve from ChatGPT, reconstruct from Cursor — same memory, same device.
NOASSERTION -
The shared brain for teams of humans and AI. Local-first MCP memory engine with hybrid FTS5 and vector retrieval.
npm MIT -
Deterministic UI/UX & shadcn/ui Intelligence MCP Server with LRU-Cached RAG Engine. Minimum-Chunk Retrieval & 0ms Latency Caching.
MIT -
nexus-kbgithub.com/KhaiTrang1995/nexus-kbupdated this year
Nexus-KB is an open-source reference architecture for building a production-grade enterprise Retrieval-Augmented Generation (RAG) and Knowledge Graph (KG) engine.
MIT ★ 1 -
Hierarchical AST codebase memory engine & MCP server. Slash context window bloat by 92% with structured semantic symbol retrieval for Claude Desktop & Cursor.
Apache-2.0 ★ 1 -
aionforge-memorygithub.com/jscott3201/aionforge-memoryupdated this year
A Rust-native agentic memory substrate built on the selene-db graph engine: a bi-temporal knowledge graph, hybrid retrieval, and an optional MCP server.
Apache-2.0 ★ 12 -
semhoodgithub.com/AhmeedGamil/semhoodupdated this year
**Stop grepping.** Find the exact code your AI agent needs by intent, not keywords. semhood is an AST-aware semantic code search engine that retrieves code by what it does, complete with call-graph context and optional LLM enrichment.
pypi MIT ★ 2 -
OpenScout is a Perplexity-inspired answer engine that turns a single question into a grounded, cited response. It combines web search, retrieval, reranking, and LLM synthesis in a lightweight Streamlit Application
MIT ★ 1 -
Local-first memory engine for coding agents (Claude Code/Cursor/Codex): SQLite+FTS5 retrieval, versioned bi-temporal memories, full-session capture, zero dependencies, MCP server
MIT ★ 83 -
A retrieval engine that refuses to guess. Register git repos and URLs, get grounded, cited answers over MCP and REST. Hybrid search, cross-encoder rerank, Postgres + pgvector.
MIT -
Production-oriented RAG and Agentic AI platform with hybrid retrieval, GraphRAG, Knowledge Graphs, ontologies, MCP, LangGraph, multi-agent workflows, context engineering, secure multi-tenancy, RAGAS/MLflow evaluation, OpenTelemetry, Redis, Kubernetes, and Helm.
NOASSERTION