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.
-
MCP stdio server for Windsurf that routes tool calls to a local llama.cpp llama-server (GGUF), optimized for low-VRAM GPUs.
★ 1 -
llama-mcp-servergithub.com/ahays248/llama-mcp-serverupdated this year
MCP server bridging Claude Code to local llama.cpp
npm MIT -
MCP server bridge for Claude and llama.cpp - Connect Claude Desktop to your local models
npm CC0-1.0 -
mcp-llama-swapgithub.com/oussama-kh/mcp-llama-swapupdated this year
MCP server for hot-swapping llama.cpp models in Claude Code - launchctl (macOS) + systemd (Linux)
pypi Apache-2.0 ★ 5 -
llama.cpp's llama-server + Web UI, compiled natively for your exact CPU/GPU in Docker, with a hardware guard and private local web search (SearXNG + MCP).
MIT ★ 2 -
TranslateGemmaMCPgithub.com/woheller69/TranslateGemmaMCPupdated this year
MCP server and WebUI for TranslateGemma running via llama.cpp
MIT ★ 3 -
llamacpp-mcpgithub.com/lukasmki/llamacpp-mcpupdated this year
An MCP (Model Context Protocol) wrapper for running local LLMs using llama-cpp-python
MIT ★ 4 -
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 -
maldroidgithub.com/yayaya142/maldroidupdated this year
Local MCP-enabled CLI for secure, static-only Android artifact investigation with llama.cpp
MIT -
locogithub.com/ilovepixelart/locoupdated this year
MCP server for local LLMs — Ollama, LM Studio, llama.cpp
MIT -
Native Mac resources behind one MCP endpoint: Metal rendering, CoreML, VideoToolbox, llama.cpp.
Apache-2.0 -
MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware
MIT ★ 19 -
Локальный OCR на GPU: llama.cpp + GLM-OCR. Горячая клавиша, трей, фоновая модель, MCP-сервер. Windows
-
searxng-mcp-bridgegithub.com/designcomputer/searxng-mcp-bridgeupdated this year
Minimal SearXNG->MCP streamable-HTTP bridge for the llama.cpp WebUI
MIT ★ 7 -
Profile llama.cpp-family GPU inference, run controlled experiments, and compare results with evidence labels. CLI, MCP server and Agent Skill.
MIT ★ 1 -
Domain-pluggable LLM agent runtime with tool permissions, human approval, MCP server, and a repeatable eval harness. Local models (llama.cpp) and hosted APIs.
MIT -
web-search-addon-for-offline-llmgithub.com/Fateh-Studio/web-search-addon-for-offline-llmupdated this year
RAG + offline MCP Server for llama.cpp and LM Studio | web search during Iran internet disruptions
NOASSERTION ★ 1 -
Strata 125B MoE + JEV mode: llama.cpp fork with parallel-decision endpoints (yes/no in ~10ms), an MCP server, and a llama-swap router swarm for Claude Code & DeepSeek Harness.
MIT ★ 1 -
Serve, size and benchmark open LLMs on one 16 GB GPU: vLLM vs llama.cpp vs Ollama, KV cache and offload planning, MCP server
MIT -
Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp
★ 1 -
llm-stackgithub.com/KI7MT/llm-stackupdated this year
Local LLM + 42 ham radio MCP tools in a browser — Docker Compose reference stack (Open WebUI + llama.cpp + qso-graph MCP servers)
-
Local MCP server exposing the Cloudflare Clef-Flash decision model to AI agents — structured decisions with probability outputs, fully offline via llama.cpp.
npm Apache-2.0 ★ 8 -
Question answering over your documents with cited sources: FastAPI + SSE, retrieval over MCP (cMCP + cRAG), local LLM via llama.cpp, evaluation gated in CI
MIT ★ 1 -
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 -
KINDXgithub.com/ambicuity/KINDXupdated this year
Local-first hybrid cli search engine (BM25 + Vector) for personal knowledge bases and agentic workflows. Runs entirely on-device via node-llama-cpp.
npm MIT -
Agente LLM local e Servidor MCP em Python (Anthropic MCP SDK + llama.cpp nativo Windows) com sandbox de segurança, rotinas YAML e bateria de avaliação contra prompt injection
-
MCP server that delegates mechanical tasks to local OpenAI-compatible inference backends (llama.cpp, Ollama, etc.) and provides context-management tools (compaction, scratch store, token estimation).
MIT ★ 1 -
Self-hosted long-term memory for AI agents: a Supermemory-shaped API, fact extraction with temporal truth, MCP server and web console, on local llama.cpp servers.
NOASSERTION -
Find files by what's in them: photos, PDFs, docs, voice memos and video, on your own computer. EmbeddingGemma 2 + llama.cpp; CLI, app and MCP server for agents.
MIT ★ 9 -
opencode-memorygithub.com/rajarshighoshal/opencode-memoryupdated this year
Persistent semantic memory for AI coding agents — a single Rust MCP server over SQLite + sqlite-vec with local llama.cpp embeddings. Works with opencode, Claude Code, and Codex.
cargo MIT ★ 2 -
MCP server that estimates, trims and compacts context to keep any OpenAI-compatible endpoint (oMLX, Ollama, llama.cpp, LM Studio, vLLM, OpenAI) under its context window.
pypi MIT -
Local-inference layer for coding agents: your files are read by llama.cpp on your machine, not by your agent's context. MCP, rootless Podman, no egress, cited answers, measured.
GPL-3.0 -
macOS Computer Use MCP Server - 33 tools for screen control via Model Context Protocol. Works with Claude Code, Cursor, LM Studio, Ollama, llama.cpp, MLX, and all MCP clients.
MIT ★ 1 -
MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestrator session.
MIT ★ 19 -
grepaigithub.com/vp2722/grepaiupdated this year
🔍 GrepAI - Local AI-powered codebase search MCP Server. Self-hosted MCP server with GPU-accelerated LLM support (llama.cpp/vLLM). Search, analyze, and navigate your codebase with Claude Code or any MCP-compatible AI agent. One-command installation.
MIT -
llama-mcpgithub.com/DaWasteh/llama-mcpupdated this year
🔌 Zwei getrennte MCP-Server für llama.cpp: gehärteter Dateisystem-Zugriff und sichere Internet-Recherche (DuckDuckGo, Wikipedia, arXiv)
MIT -
Runs CodeZaiku, a coding and development harness on local models (Ollama, llama.cpp) or hosted APIs, as an MCP server, so Claude Code, Codex or Gemini CLI can hand it coding, review and ops tasks.
npm Apache-2.0 -
light-OCR-modulegithub.com/dwain-barnes/light-OCR-moduleupdated this year
Local OCR that turns scanned PDFs and images into clean Markdown — powered by LightOnOCR + llama.cpp. 100% on-device, no cloud, no API keys. Python library, CLI, MCP server, and Claude Code skill in one package
MIT -
MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_claims, get_claim, list_measured. Read-only, CC BY 4.0 data.
Apache-2.0 ★ 4 -
AI browser agent in Chrome's side panel, powered by a model on your own PC (Ollama, LM Studio, llama.cpp, vLLM). No account, no telemetry. Opt-in CAPTCHA solver, scheduled tasks, /test bug reports, and an MCP server for Claude Code.
MIT -
Self-hosted semantic code search MCP server for Claude Code, Cursor, Codex and Copilot. Indexes many repos locally with tree-sitter AST chunking, a symbol graph (find usages) and git history, on Qdrant + local llama.cpp embeddings. Your code never leaves your machine. MIT.
go MIT ★ 34 -
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
NOASSERTION ★ 151 -
Mirror your body in data. One standard, every source, one complete picture of you: a self-hosted health record built from lab reports, wearables and genetics, with every number traced to its source and a built-in MCP server. Run it with Docker and one LLM key, or keep every model local on llama.cpp.
pypi Apache-2.0 ★ 1,525 -
Open-source deep research assistant with citations and memory. Ask a question and it searches the web, papers, old newspapers, archives and GitHub, writes a report, checks its citations against the sources, and keeps what it found. Use it for a literature review or your family tree. It runs with a local LLM (Ollama, llama.cpp) or a hosted API.
npm Apache-2.0 ★ 1 -
codeindex.mcpgithub.com/mishkidreams/modelcontextprotocolupdated this year
MCP server for semantic code indexing with Qdrant and llama.cpp. Provides tools for indexing Git repositories and semantic code search.
nuget MIT -
Native C++/Rust code editor for the AI era — Linux/macOS/Windows, ~13 MB bare binary, 238 file extensions / 82 language lexers, Rust-powered search, 6 AI backends (Ollama / llama.cpp / OpenRouter / Ollama Cloud / OpenAI / Azure OpenAI), 49-tool MCP server. Free forever, GPL-3.0.
cargo GPL-3.0 ★ 7 -
A compiler for the code AI agents write: a flat SSA language with JSON diagnostics, compiled in under a millisecond to sandboxed native code, as MCP tools. Its Llama 3.2 1B prefills 1.7-2.4x faster than llama.cpp.
Apache-2.0 ★ 1 -
diaMCPgithub.com/chartrambiz/diaMCPupdated this year
An all-in-one MCP server exposing file operations, web search, git operations, shell commands, code execution, and custom tools via HTTP. Designed for llama.cpp webui integration.
MIT ★ 20 -
This is the CtrlAsistent MCP (Model Context Protocol) server, which works with any MCP client: - llama.cpp - OpenCode - DSH Harness - Pi Harness - Claude Desktop - and others
MIT -
Claude Code plugin: MCP server that offloads bounded LLM tasks to cheaper local (LM Studio, Ollama, vLLM, llama.cpp) or remote (OpenRouter) models with profile-based configuration and ensemble mode
MIT ★ 1 -
local-llm-delegategithub.com/faizan007jr/local-llm-delegateupdated this year
Claude Code plugin that delegates simple, well-scoped tasks to a locally running LLM (Ollama, LM Studio, llama.cpp, vLLM) via MCP
MIT ★ 1 -
Query Wikipedia ZIM archives offline with a hybrid RAG system using Llama.cpp. Build local indexes for private, internet-free knowledge retrieval.
-
Transform LinkedIn saved posts into an interactive, interconnected Obsidian knowledge graph. Features a zero-config web dashboard, hybrid LLM routing (Groq + local vLLM/llama.cpp), vector embeddings, and MCP support.
MIT -
MCP server for Blender. Hundreds of tools for modeling, materials, rendering and more, driven by Claude, Cursor, Codex, Ollama, llama.cpp, or any MCP client.
pypi MIT ★ 198 -
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 -
promptchaingithub.com/atharva557/prompt-chainingupdated this year
Load, unload, and swap any number of local LLMs (LM Studio, Ollama, llama.cpp, ...) with full client-side control — plus unified streaming for local and cloud backends and an MCP server so agents can manage your VRAM.
pypi MIT -
SharpInfergithub.com/JPaulDuncan/SharpInferupdated this year
A pure C# LLM inference engine built from scratch — no Python, no llama.cpp bindings, no ONNX Runtime. SharpInfer loads GGUF and Safetensors models directly, dequantizes weights in managed code, and runs the full transformer forward pass natively on .NET 8.
MIT ★ 6 -
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 -
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
NOASSERTION ★ 30 -
Open-source, LLM-agnostic second brain. Connect any LLM (local llama.cpp, Claude, Codex, GPT, Gemini, Grok, Ollama) via MCP — memory lives as Markdown in YOUR GitHub repo, independent of any model. Desktop, VPS or bot VM. MIT.
MIT ★ 2