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.
-
llamacpp-mcpgithub.com/lukasmki/llamacpp-mcpupdated this year
An MCP (Model Context Protocol) wrapper for running local LLMs using llama-cpp-python
MIT ★ 4 -
mcp-search-fetchgithub.com/dusklight/mcp-search-fetchupdated this year
MCP for searching the web and fetching website contents.
MIT ★ 1 -
Local-first, cognitive persistent memory & knowledge graph for AI coding agents via Model Context Protocol (MCP)
AGPL-3.0 -
Benchmark local LLM inference speed (tokens/sec) on your own hardware — llama.cpp native + cloud APIs, 124-model catalog, optimal-quant picker, and an MCP serve mode.
MIT ★ 2 -
Delegate summarize/classify/extract/triage to a FREE local Gemma-4 cascade via llama.cpp. Go CLI + MCP server; never calls a cloud model. Includes a turnkey setup skill for Claude Code.
go Apache-2.0 ★ 4 -
Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.
go MIT ★ 7 -
LLM routing proxy for coding harnesses. Auto-routes to cloud or local inference via Bonsai LLM classification. Fallback, prompt rewriting, MCP code review, Signal/Discord Remote Communication
★ 7 -
SQLite entity/fact/alias knowledge graph, CSV/JSON data importer, budgeted per-turn context injector, chat-history normalizer, and MCP server for local LLMs (4B-9B)
MIT -
Deterministic SQLite memory engine, physically sharded multi-tenant state graph, pre-turn context compiler & MCP server for local LLMs/SLMs (4B-14B) — zero vector DB
MIT -
Your coding agent, but your other PCs do the heavy lifting. A per-machine LAN daemon that lets any MCP-capable agent delegate tasks to local models on your other home machines. No cloud, mutual-TLS, MCP-native.
Apache-2.0 ★ 2 -
Mult-Hands-Eyes-MCPgithub.com/MicroHEROX/Mult-Hands-Eyes-MCPupdated this year
MCP server that gives online LLMs local hands and eyes: OpenAI-compatible local inference (KoboldCpp / Unsloth / llama.cpp / LM Studio / Ollama) for cheap text work and vision work (OCR / image analysis / comparison).
npm MIT -
Profile-based launcher for local LLM servers - start, stop and switch models on llama.cpp, Ollama and LM Studio from one CLI/TUI. Zero resident overhead, optional MCP control plane, importable as a Go library.
MIT ★ 2 -
local-fusiongithub.com/kelvincushman/local-fusionupdated this year
Local OpenRouter-Fusion-style multi-model council: panel + judge + synthesizer over local OpenAI-compatible servers (Ollama/LM Studio/llama.cpp) and/or Pi subscription models. Includes an MCP server for Claude Code. Zero-dependency Node + Python.
MIT -
AnyLoom-AnythingLLM-Local-AI-agentic-DyTopo-swarmgithub.com/Intradyne/AnyLoom-AnythingLLM-Local-AI-agentic-DyTopo-swarmupdated this year
ChatGPT-like AI that runs 100% locally on your hardware. No subscriptions, no cloud, complete privacy. Multi-agent swarm + 10 MCP tools + hybrid RAG vector DB + . Runs on one GPU (RTX 5090 recommended)
MIT ★ 11 -
Fullstack_MCP_hubgithub.com/jbulger82/Fullstack_MCP_hubupdated this year
Fullstack MCP Hub — Complete MCP toolkit with built in RAG, GUI and 50+ free tools (no paid APIs) that runs out-of-the-box. Works with Gemini CLI, OpenAI/Codex CLI, ChatGPT (dev mode), Claude, local LLMs, and anything that can connect to an MCP server—basically “Claude-level” tool power for local models.
★ 1