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.
-
@muhammadmehdi/ollama-mcp-servergithub.com/m-mehdi14/ollama-mcp-serverupdated this year
Universal MCP server for Ollama - Works with ANY IDE or application that supports Model Context Protocol (MCP). Compatible with Cursor IDE, Claude Desktop, Cline, and all MCP-compatible clients. Provides tools to list models, chat, generate text, and mana
npm MIT -
ollama-mcp-chat-cligithub.com/Shahrukh19S/ollama-mcp-chat-cliupdated this year
A terminal MCP chat agent on a free local model (Ollama) with Groq/GitHub fallbacks - implements an MCP Server (tools, resources, prompts) and an MCP client with an agentic tool-calling loop via LiteLLM
MIT -
Example MCP client and server with Quarkus, Langchain4j and Ollama.
★ 3 -
Query model running with Ollama from within Claude Desktop or other MCP clients
pypi MIT ★ 34 -
MCP Server and MCP Client - Using local Ollama
-
an custom mcp server and custom mcp client project powered by ollama's llama 3.2
-
Drop-in HTTP proxy for Ollama with priority queuing, per-client auth, and model-aware failover
MIT ★ 3 -
Simple MCP server and client in Node.js using Ollama for local LLM-based filesystem operations.
MIT ★ 1 -
MCP stdio server exposing Ollama's hosted web search and web fetch APIs as tools for any MCP client.
pypi MIT -
MCP servers for Protein Data Bank, ChemBL, and other life science data (WIP), with Ollama client for local testing.
★ 12 -
Stdio MCP server exposing Ollama Cloud web search and web fetch as tools for Claude Code, Codex CLI, ZCode and any other MCP client. Zero dependencies.
npm MIT -
ollama-agent-kitgithub.com/niceunderground/ollama-agent-kitupdated this year
Minimal Node.js agent loop for Ollama: local LLMs that read/write/edit files, run shell commands, and call MCP tools. MCP client and server, two dependencies, fully offline.
MIT ★ 2 -
Optional MCP servers (Ollama, Windows Sandbox) for Combwork or any MCP client
MIT ★ 1 -
Private, offline chat client for uncensored local LLMs. Zero dependencies, 228 tests, MCP server. Node + Ollama.
MIT -
MCP server that lets Claude Code (or any MCP client) delegate sub-tasks to a local Ollama model
MIT ★ 1 -
Ollqdgithub.com/leomarviegas/Ollqdupdated this year
MCP client-server RAG system — index codebases & documents into Qdrant using Ollama embeddings, with code-aware chunking and interactive chat
Apache-2.0 -
a knowledge-graph and RAG system that extracts requirements into neo4j, queryable through an ollama and MCP chat client with RL tuned retrieval strategies.
-
A Crystal MCP server that indexes project documentation via Ollama embeddings and exposes hybrid search (semantic + keyword) to MCP clients.
MIT ★ 1 -
VLC MCP server & Claude Code plugin: control VLC Media Player from Claude, ChatGPT, Ollama and any MCP client
npm MIT -
MCP server + Ollama-driven autonomous penetration testing client. Connects LLMs to security tools (nmap, nikto, sqlmap, dalfox…) via Model Context Protocol with session management, output parsing, and findings persistence.
GPL-3.0 ★ 14 -
cortexgithub.com/Gustav-Proxi/cortexupdated this year
Local-first MCP server giving any LLM client semantic + literal search and full read/write over an Obsidian/markdown vault. Local embeddings via Ollama, sqlite-vec index.
Apache-2.0 -
mcp-rag-servergithub.com/agarwalvishal/mcp-rag-serverupdated this year
MCP RAG server — local embeddings, your docs never leave your machine. Private knowledge base + web search for Claude, Cursor, and Ollama. Drop your docs, connect your AI client, done.
MIT ★ 6 -
Self-hosted memory for your LLM conversations: import your chat archives and documents, search them, and chat over them on your own machine with Ollama and share that memory with any MCP client.
Apache-2.0 -
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 -
bigmac-mcpgithub.com/TrueNorthIT/bigmac-mcpupdated this year
Turn a shared Ollama box into a team resource for Claude Code (or any MCP client): typed local-LLM tools + delegated, read-only repo exploration. Keep your frontier agent on its subscription; run the grunt work locally for free.
MIT -
Give your AI agent ears that know who's talking: a local, hands-free voice front-end that names speakers. Works with OpenAI, OpenClaw, Hermes Agent, Ollama and any MCP client.
Apache-2.0 -
🤖 Agente de IA que atende os clientes do Bazar sem nunca repassar o token: MCP + troca de token (RFC 8693), confirmação humana, avaliações com modelos reais no CI. Python · LangGraph · MCP · Ollama · Keycloak · OpenTelemetry
-
Simple Fact Checker Model-Context-Protocol Server, Client, and Ollama models
MIT ★ 5 -
AI agent for rich text editors: let Ollama, OpenAI-compatible models, Claude or any MCP client (Claude Desktop, Claude Code, Cursor) read and edit a document, with every edit shown as a suggestion to accept or reject.
npm MIT -
Create a Chatbot using Ollama, qwen3, gemini web search project, MCP server/client by creating tools.
-
A local AI chatbot using Django, Ollama, Qwen, and MCP integrates with a Laravel 12 blog. Django acts as the MCP client, while Laravel provides tools for blog operations. The LLM decides when tools are needed, and Laravel handles requests using services, Eloquent, and MySQL.
-
justthreedgithub.com/phanikondru/justthreedupdated this year
MCP server that exposes Blender control tools to AI clients (Claude, Gemini, Cursor, Ollama, and more)
pypi MIT -
A MCP provider Deepseek reasoning content to MCP-enabled AI Clients, like Claude Desktop. Supports access to Deepseek's CoT from the Deepseek API service or a local Ollama server.
★ 69 -
memory-ia-mcpgithub.com/helciocosta/memory-ia-mcpupdated this year
Servidor MCP (Model Context Protocol) em Python para agente de IA com memória persistente, integrando FastAPI, LangGraph, SQLite e modelos locais via Ollama, pronto para uso em VS Code, Gemini-CLI e outros clientes MCP.
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 -
AutoPentest-MCPgithub.com/aamirizwann/AutoPentest-MCPupdated this year
Autonomous-pentest MCP server — one-command install of 140+ security tools (Pentest-MCP + HexStrike + MobSF) with auto-wired AI clients (Claude Code, Gemini CLI, OpenAI, DeepSeek, Ollama).
NOASSERTION ★ 2 -
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 -
ctx-sysgithub.com/david-franz/ctx-sysupdated this year
Local hybrid RAG over a code knowledge graph. Indexes your codebase with tree-sitter + embeddings + a relationship graph and serves precise context to any AI assistant over MCP — fusing keyword (FTS5), vector, and graph search with reciprocal rank fusion. Local-first via Ollama; works with Claude Code, Cursor, and any MCP client.
MIT ★ 15 -
chrome-mcp-servergithub.com/syedazharmbnr1/chrome-mcp-serverupdated this year
Chrome Browser MCP Server — 18 tools for browser automation via Model Context Protocol. Screenshots, DOM access, JS eval, network monitoring, form filling, GIF recording. Works with Claude Code, Cursor, LM Studio, Ollama, llama.cpp, any MCP client.
-
bokigithub.com/edrin09/bokiactive
BOKI — offline-first open-source accounting software with open AI: bring your own LLM (local Ollama / on-prem / cloud, OpenAI-compatible), read-only MCP for external AI clients, AI writes drafts only — humans approve. SQLCipher-encrypted local DB, zero egress, runs without network. 离线优先的开源财务软件:开放式 AI,模型随你换,数据不出门,AI 只写草稿
AGPL-3.0 ★ 8 -
genesis-agentgithub.com/Garrus800-stack/genesis-agentupdated this year
Self-aware cognitive AI agent with a persistent soul: reads, modifies & verifies its own code, plans autonomously, dreams in idle time, remembers across sessions (episodic memory + Obsidian vault bridge). Emotional state, trust levels, MCP server & client. Runs on Claude, GPT or local Ollama models. Electron desktop app (Windows/macOS/Linux).
MIT ★ 43 -
31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.
npm MIT ★ 6 -
A local AI assistant powered by Ollama and Llama 3, using MCP to intelligently handle tool-based tasks alongside general questions.
-
Ollama-MCPServer-pythongithub.com/naseemap47/Ollama-MCPServer-pythonupdated this year
Personal Agentic AI Assistant - build with Ollama, MCP, FastAPI frameworks.
MIT -
ollama-mcpgithub.com/rawveg/ollama-mcpupdated this year
An MCP Server for Ollama
npm AGPL-3.0 ★ 179 -
This repo presents MCP server for localized Ollama using Gradio
Apache-2.0 -
DocuMindgithub.com/nmdra/DocuMindupdated this year
Fully local RAG agent built with FastMCP + ChromaDB + Ollama model.
★ 1 -
Sphraivagithub.com/Codibex/Sphraivaupdated this year
—
MIT -
korgi-vision-ossgithub.com/c0de4un/korgi-vision-ossupdated this year
Open-source, self-hosted platform for distributed image analysis using local Vision LLMs (Moondream 2 / Qwen 2.5). Built with Rust, Axum, and Vue 3.
MIT ★ 1 -
ai-testcase-generatorgithub.com/VenkateshDoijode/ai-testcase-generatorupdated this year
AI-driven CLI toolkit that generates and manages Jira Zephyr Scale test cases using HuggingFace/Ollama — generate, import, update, link, and report.
★ 3 -
Turn your repository into local RAG / MCPServer.
MIT ★ 9 -
mcp-rag-chroma-streamlitgithub.com/CyprianFusi/mcp-rag-chroma-streamlitupdated this year
A production-ready Retrieval-Augmented Generation (RAG) application built with Streamlit, LangChain, and ChromaDB. Features Model Context Protocol (MCP) integration for seamless tool calling and supports multiple LLM providers including OpenAI and Ollama.
MIT -
Airbnb-StockScreener-Agent-with-MCPgithub.com/ambideXtrous9/Airbnb-StockScreener-Agent-with-MCPstale
StockScreener MCP with Langchain
-
A natural language interface to databases powered by local LLMs via Ollama. Chat with your data using plain English instead of SQL.
MIT -
Build AI Agent using Google ADK , MCP and Gemma 3 model
MIT ★ 27 -
My-simple-mcp-client-and-servergithub.com/hubgitub/My-simple-mcp-client-and-serverupdated this year
A simple local Ollama CLI supporting MCP with a MCP server
-
A tiny, keyless, zero-Docker Tavily API mock server & MCP tool for local LLMs (Ollama, Goose, Aider). Backed by DuckDuckGo with TTL caching, single-flight dedupe, and clean page text extraction.
pypi MIT -
mcp-discord-assistantgithub.com/Jlassi-Mohamed/mcp-discord-assistantupdated this year
A powerful Discord management assistant leveraging the Model Context Protocol (MCP) and Ollama for local, privacy-first intelligence. This project provides multiple interfaces to interact with your Discord server, including a custom Streamlit dashboard and direct integration with Claude Desktop.
MIT -
LLM-controlled network protocol servers & clients (~290 servers, ~250 clients) with an MCP server mode. Launcher that runs the platform-native netget binary.
npm AGPL-3.0-or-later -
A Beta for AI CLI tools integration for WordPress + Deep MCP Integration via the AI Engine Plugin
MIT ★ 2