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.
-
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 -
Your StackChan, your language model, your network — local-first firmware and server kit for the M5Stack StackChan. Voice, face, camera and MCP tools, with nothing sent to a cloud service.
MIT ★ 5 -
A sleek C# class library designed to integrate a local Model Context Protocol (MCP) server with a local Large Language Model (LLM), tailored for Godot-based games. This library empowers your LLM to seamlessly interact with the game world through structured tool commands, bringing your Echoes of Ir-style vision to life.
MIT ★ 1 -
local-llm-mcp-toolgithub.com/Marcel-MSC/local-llm-mcp-toolupdated this year
—
MIT -
Local LLM MCP - A FastMCP compliant server for local LLM management and integration
MIT ★ 2 -
mcp-local-llmupdated this year
MCP server that uses a local LLM to respond to queries - Binary distribution
npm MIT -
MCP server for local LLM with Cursor agent validation and speculative decoding
GPL-3.0 -
本地模型管家 MCP:管理 GGUF 模型与 llama-server —— 模型台账 / 显存估算 / 服务生命周期 / chat 代理(FastMCP)
MIT -
Local LLM deployment using Docker, Ollama and a custom MCP server with REST-based API integration.
-
local-llm-mcpgithub.com/ryu111/local-llm-mcpupdated this year
High-performance MCP Server for local LLM models on Apple Silicon, featuring MLX integration with IQuest-40B
-
MCP server for local LLM inference on Ryzen AI Max+ 395 with queueing, deadlines and telemetry; benchmark findings
MIT -
This is a local LLM provider, include rag-mcp and agent features, can load HF/gguf/onnx model formats..
Apache-2.0 -
MCP server to fine-tune LoRA, export GGUF, and deploy local LLMs on Onde Inference.
npm -
This is the code used to integrate a local LLM with Blender for generating 3D models using text prompts.
★ 1 -
MCP server for offloading tasks to local LLMs via LM Studio SDK - now with context-aware prompts, diagnostics, and bug fixes
npm MIT -
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 -
MCP server for delegating mechanical tasks to local LLMs via Ollama. Claude does the thinking, your local model does the grunt work.
npm MIT ★ 15 -
mcp-memoria-para-llm-localgithub.com/JM7087/mcp-memoria-para-llm-localupdated this year
Servidor MCP (Model Context Protocol) de memória persistente para LLMs, implementado em PHP com SQLite.
MIT -
Small MCP servers that give a local LLM live world events, market data, a dependency audit, a study coach and equation OCR
MIT -
MCP server that hands private-data or large-output work to a local LLM: the cloud model gets sanitized digests and stable placeholders, the material never leaves your network
MIT ★ 1 -
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
npm MIT -
local-llm-delegation-mcpgithub.com/mrrodriguez/local-llm-delegation-mcpupdated this year
Intelligent task delegation for AI agents: Offload the "easy" work to your local machine and save premium tokens for the hard stuff.
★ 1 -
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
-
local-llm-speakergithub.com/geoClink/local-llm-speakerupdated this year
Private, offline smart speaker built from scratch. Raspberry Pi 5 brain running Whisper STT, Ollama + Qwen3, and Piper TTS. MCP tools for weather, sports, and BBQ probe. Web dashboard for full control. No cloud. No subscription. No voice data leaving your network.
-
local-llm-mcpgithub.com/HenryLinyy/local-llm-mcpupdated this year
MCP server that lets Claude Code & Codex delegate bounded, token-heavy generation to local or cheap-cloud LLMs — LM Studio · Ollama · vLLM · llama.cpp · DS4, plus DeepSeek/OpenRouter/Groq/Cerebras/MiniMax/Agnes. Keep the frontier agent's judgment, cut the token bill, with RAM guards and a text-only safety boundary.
MIT ★ 3 -
依 Model Context Protocol 實作 local-first 委派伺服器:7 個 tools(6 純本機加 1 個需另設金鑰的 opt-in 雲端搜尋)、1 個 resource 與 2 個 prompts,支援 stdio 與 Streamable HTTP、Bearer API Key 驗證與 map-reduce 摘要進度回報,並完成四家 client 實測。RTX 4090 上 1,332 字長文摘要 Qwen2.5-3B 0.63s、TAIDE-8B 1.21s
MIT -
my-local-storage-mcpgithub.com/avm-sistemas/my-local-storage-mcpupdated this year
A pragmatic, low-overhead Model Context Protocol (MCP) server that provides Large Language Models (LLMs) with a persistent, local long-term memory.
GPL-3.0 ★ 4 -
A distributed LLM architecture combining local language models, Model Context Protocol (MCP), and Azure Table Storage. Features OpenAI-compatible APIs, tool calling, and real-time streaming for AI-powered data querying.
-
Local data workbench a local language model drives over MCP: ingest, versioned cleaning, quality rules, charts, dashboards as code and quick models. Part of the Hoard family.
MIT -
recursion-mcpgithub.com/netflypsb/recursion-npxupdated this year
Recursive Language Model MCP server for unbounded document processing with local RAG
npm MIT -
Exact arithmetic, symbolic math, units, dates, statistics and SQL-over-files for local language models: every computation logged with an id the model cites and a person can re-run. FastAPI + React, MCP tool server included.
MIT -
A local studio to tune and extend language models: versioned datasets, LoRA and QLoRA training on the allowed GPUs, merges, GGUF conversion, importance-matrix quantization, YaRN context extension and evaluation against the base model. MCP tools for assistants.
MIT -
mcp-ollama-notesgithub.com/KodavatiAnisha/mcp-ollama-notesupdated this year
Local LLM Note System is a lightweight, AI-powered note management application built using FastAPI and a locally running Large Language Model (LLM) via Ollama. The system allows users to create, store, and manage notes efficiently while enabling AI-assisted interactions such as summarization or content processing.
MIT -
This repository contains an experimental and educational project demonstrating how to build a financial AI agent using a local Large Language Model (LLM) and a custom tool server.
-
Repair broken or incomplete JSON, including output from language models. Local CLI and MCP server. No API key.
MIT -
KnowledgeManager_MCPgithub.com/Big-ShahMir/KnowledgeManager_MCPupdated this year
A highly efficient local server that implements the Model Context Protocol (MCP). It acts as a bridge, providing Large Language Models (LLMs) with direct, tool-based access to a curated knowledge base built from local PDF documents.
-
mcp-excel-server is a project based on the Spring AI MCP framework. Its main function is to provide large language model (LLM) with the ability to read and write local Excel files with the help of MCP protocol.
★ 7 -
audio-mcpgithub.com/ehm-93/audio-mcpupdated this year
A local MCP server that lets a language model design, edit, analyze, and batch-export game sound effects
MIT-0 -
FileAsist, a file organization agent running on small language model, on your local, reading you files, understanding them and organizing it based on your preferences.
★ 1 -
Fast local code search, source reads, and smart block-clamped context for AI coding agents. VS Code Native Language Model Tools & MCP server backed by a shared Rust trigram cache (Linux, Windows, WSL).
MIT -
llm_mcpgithub.com/AuraFriday/llm_mcpupdated this year
MCP server that runs local LLMs (with full access to MCP tools included). Callable by Python to chain MCP tools with local intelligence.
Apache-2.0 ★ 3 -
Web search and persistent memory MCP servers for local LLM coding agents (Python)
MIT -
Private, offline chat client for uncensored local LLMs. Zero dependencies, 228 tests, MCP server. Node + Ollama.
MIT -
Dependency-free MCP servers: semantic search over an Obsidian vault and local-LLM delegation via Ollama
MIT -
Evaluation and runtime governance layer for local LLMs (Ollama + MLX-LM): deterministic policy/provenance guardrails, MCP server, regression gate, and reviewer console
★ 1 -
Fully local AI stack in Docker Compose — Ollama LLM inference, SearXNG private metasearch, Firecrawl scraping + real browser automation, and Langfuse observability behind one authenticated gateway with an MCP tool interface. No cloud calls, your data stays on your hardware.
MIT -
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
npm MIT ★ 2 -
Let LLMs manage your local dev environments
★ 28 -
ucp-localgithub.com/akshay2211/universal-context-pipelineupdated this year
Universal Context Pipeline — local-first MCP server for grounding LLMs in your files
cargo Apache-2.0 -
Zero-cost Go MCP server giving local LLMs (Ollama, Qwen, LM Studio) safe web search, clean Markdown extraction, CDP browser fallback & SSRF defense
-
Save and resume your LLM work. A local-first MCP server that turns a long chat into a versioned, resumable project state. Two commands: Savepoint. Resume.
NOASSERTION ★ 2 -
locogithub.com/ilovepixelart/locoupdated this year
MCP server for local LLMs — Ollama, LM Studio, llama.cpp
MIT -
MCP server providing LLMs direct access to local package source code to eliminate API hallucinations
npm MIT ★ 1 -
Local-first GraphRAG over a markdown knowledge base: LightRAG, Ollama/Qwen, MCP server, LLM router, scheduled self-maintenance
MIT -
A simple MCP server that reads local images and returns them as ImageContent for LLM vision analysis
pypi MIT -
A simple, locally hosted Web Search MCP server for use with Local LLMs
npm MIT ★ 1,207 -
MemOS - Universal local-first persistent memory layer for AI agents and LLMs
npm MIT ★ 10 -
Stealth browser for AI agents that runs on small local models. Read any site as Markdown, log in without an LLM, MCP server included.
pypi MIT ★ 7 -
Local-first SEC 8-K research lab: score filings point-in-time with Jev, OpenAI or local LLMs, and label which results can count as evidence. Never places orders.
MIT -
Alpha MCP server for local-first LLM orchestration: memory, knowledge, state, routing, swarm planning, API discovery, tests, automation, and plugins.
npm MIT ★ 2