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.
-
A project showcasing connectivity between a Web API Server, MCP Server, Ollama using SSE.
Apache-2.0 ★ 1 -
ollama-web-tools-mcpgithub.com/chakkritte/ollama-web-tools-mcpupdated this year
Claude Code MCP server for web search and fetch. Supports Ollama's hosted API instance.
MIT ★ 2 -
A Node.js MCP server exposing Ollama's web search and web fetch APIs as MCP tools
npm MIT -
Run local Ollama models as an MCP server so an agent can send work to a model on your own machine instead of an API.
npm Apache-2.0 ★ 2 -
MCP server with web search tool using Ollama's API. Enables AI assistants to search internet via standardized protocol. Ruby implementation with error handling and result formatting.
MIT ★ 1 -
MCP stdio server exposing Ollama's hosted web search and web fetch APIs as tools for any MCP client.
pypi MIT -
MCP server for Ollama web search and web fetch APIs. Enables AI assistants like Claude Desktop to search the web and fetch webpage content.
pypi MIT ★ 1 -
ollama-bridge-mcpgithub.com/ElnurIbrahimov/ollama-bridge-mcpupdated this year
MCP server that gives Claude Code 27 AI brains via Ollama — 15 cloud + 12 local models. Auto-routing, batch comparison, smart delegation. Reduce API costs, get specialized models for code, math, vision, reasoning.
MIT -
Local MCP integration for a luxury watch market data API using Ollama, FastAPI, Cloudflare Workers, Hyperdrive, and Supabase PostgreSQL.
-
API service to search vectorized Cursor IDE chat history using LanceDB and Ollama
★ 4 -
adaptoragithub.com/guptayush02/adaptoraupdated this year
Self-hosted Dynamic API Agent with an MCP layer — talk to any REST API in natural language. Bring-your-own-LLM (Ollama).
MIT ★ 1 -
Give your local LLM internet search — no API keys, no rate limits. Self-hosted SearXNG + FastAPI middleware for LM Studio & Ollama.
★ 2 -
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 -
@systemmin/image-mcpgithub.com/systemmin/image-mcpupdated this year
视觉识别 MCP 服务器,支持 Claude (Anthropic)、智谱 (GLM-4V)、Ollama 三大视觉 API
npm MIT -
用中文描述完成剪辑,保留可编辑时间线。Kdenlive fork with Codex, compatible AI APIs, Ollama and WorkBuddy MCP.
GPL-3.0 -
A local, sovereign long-term memory for AI agents: MCP server + CLI on Qdrant and Ollama. No cloud, no API bill.
MIT ★ 1 -
memexgithub.com/vndee/memexupdated this year
Local-first temporal knowledge graph memory for AI agents. Runs with Ollama — no API keys required. Single Go binary + SQLite. Hybrid search, MCP server, REST API, interactive TUI.
go MIT ★ 3 -
Serveur MCP TypeScript (29 outils, 404 tests) : Ollama, Git, APIs, web, actu RSS/Bing/officiel, RAG. Projet perso reconversion IA - Peter UFENS.
MIT -
An MCP-compatible service that provides real-time weather and location data via the OpenWeather API. Built for easy integration with Claude Desktop and Ollama (Qwen 2.5).
★ 2 -
🗓️ AI Calendar Assistant powered by local LLM (Ollama) + Google Calendar API + MCP
MIT ★ 6 -
rag-mcp-servergithub.com/ElnurIbrahimov/rag-mcp-serverupdated this year
RAG MCP server for Claude Code — hybrid search (vector + BM25), code-aware chunking, PDF support. Uses Ollama nomic-embed-text + LanceDB. Fully local, zero API costs.
MIT -
WhatsApp Messaging with MCP & Ollama This project integrates PraisonAI Agents with Ollama (llama3.2) and a Go-based WhatsApp bridge. It allows you to send WhatsApp messages using natural language through a local REST API, powered by an LLM and custom MCP tools.
MIT -
Local-first MCP server: 17 AI tools + 5 system endpoints for Claude & Cursor, powered by Ollama — all inference on-device, no API key, no data egress.
MIT -
js-vector-store-headlessgithub.com/mauricioperera/js-vector-storeupdated this year
Headless semantic search API powered by js-vector-store and local Ollama embeddings. Vector + BM25 + Hybrid search with MCP and REST endpoints.
npm MIT -
AI usage gateway with per-team API keys, budgets, usage logging, alerts and a read-only MCP server. Runs on local Ollama or Claude
-
Servidor MCP que expone una base GraphRAG local (LightRAG + Ollama) a Claude Code en VS Code. Privado, sin nube, sin claves de API.
MIT -
Private web search MCP: SearXNG metasearch → ML reranking → 4-tier fetch cascade (Firecrawl / Crawl4AI / raw / Wayback) with per-domain learning, Ollama query expansion and synthesis. No cloud APIs.
npm MIT ★ 29 -
ableton-mcpgithub.com/jpoindexter/ableton-mcpupdated this year
Control Ableton Live with AI - 200+ tools via MCP, REST API, and Max for Live. Works with Claude, Ollama, OpenAI, Groq.
MIT ★ 60 -
Real-time and historical metrics for locally served LLMs (Ollama and vLLM) — dashboard, HTTP API and MCP server. One process, one SQLite file, never in the request path.
Apache-2.0 ★ 1 -
zbxmcpgithub.com/Monzphere/zbxmcpupdated this year
Native Model Context Protocol (MCP) server for Zabbix with an embedded AI assistant. Auto-generates API tools from the installed Zabbix version, enforces RBAC, supports OpenAI/Anthropic/Gemini/Ollama.
MIT ★ 6 -
Zero-API Facebook & Instagram Autonomous Studio powered by Playwright Persistent Context, yt-dlp, FFmpeg, 82-Rule Humanizer, Local Ollama, and Claude/Cursor MCP Server
MIT -
memory-mcpgithub.com/brianchilders/memory-mcpupdated this year
Local semantic memory + time-series intelligence layer for AI abilities. Runs on Ollama — no cloud, no API keys. Gives your AI a persistent, searchable, self-improving memory backed by SQLite.
MIT ★ 3 -
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local LLM, ChromaDB RAG, MCP server, SHA-256 chained audit log. Zero API keys. Zero cloud calls.
Apache-2.0 ★ 5 -
mcp-weather-simplegithub.com/rromenskyi/mcp-weather-simpleupdated this year
Simple MCP server exposing weather tools (Open-Meteo, no API key) to local LLMs like Ollama. stdio + streamable-HTTP transports, Dockerfile, Kustomize manifests for k3s.
MIT ★ 1 -
MCP server and CLI that turn one sentence into a finished deck, doc, or dashboard — plain-text source, self-contained web page out. Runs on your own API key or fully local with Ollama.
npm MIT -
Local semantic + keyword search across your Obsidian vault and source repos. LanceDB + Ollama (bge-m3), exposed to Claude Code and Cowork over MCP. Privacy-first: no cloud, no API keys, no telemetry.
MIT -
@szcn/sentinelreviewupdated this year
AI-powered code review — security (OWASP Top 10), code quality, standards enforcement, and custom rules. 6 providers (Ollama free/local, Gemini, Groq, DeepSeek, OpenAI, Anthropic). MCP server for Cursor, Windsurf, VS Code, Claude Desktop + CLI + Node API.
npm MIT -
🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.
npm MIT ★ 16 -
Universal AI Connector for Unity. Unified C# API for OpenAI, Claude, Gemini, Mistral, Ollama + 5 more. AI agents with tool calling, built-in MCP server, editor assistant with lot of tools. One package for runtime, agents, and MCP.
MIT ★ 11 -
local-rag-mcpgithub.com/radif-ru/local-rag-mcpupdated this year
Локальная privacy-first база знаний на RAG и MCP: гибридный поиск (BM25 + векторный, слияние RRF), cross-encoder reranker, расширение запросов, FAISS, ответы локальной LLM через Ollama. Инструменты MCP (read / list / search) модель вызывает сама. Без облачных API.
-
Local multi-agent AI code reviewer powered by Ollama — 15 specialist agents review your git diff with zero API calls or cost. Outputs markdown, JSON, SARIF, or GitHub PR annotations; also ships an MCP server and a VS Code/Cursor extension.
MIT ★ 2 -
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 -
Links the built-in assistant of a PrestaShop shop running O'So MCP Server to an AI on your own computer (Ollama, LM Studio or any OpenAI-compatible server). The relay calls the shop, so nothing is opened on your network and no API key is needed.
AFL-3.0 -
MCP server for per-customer PDF document management and RAG. Ingests text, scanned and chart-heavy PDFs (PyMuPDF + Tesseract + vision model), isolates each customer in its own Qdrant collection, and returns cited answers with deep links to the original PDF page. Local-first with Ollama, or any OpenAI-compatible API.
MIT -
Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcripts, Slack & Gmail. Runs fully local on Ollama (no cloud, no API keys); queryable by any AI agent through the built-in MCP server. Postgres-backed, publishes an Obsidian-style Quartz wiki.
pypi MIT ★ 17 -
基于本地 Ollama 服务的图片分析 MCP 工具,可直接在 Claude Desktop 等支持 MCP 的应用中使用,无需 API 密钥。
MIT ★ 1 -
gollama-mcp-servergithub.com/kevensen/gollama-mcp-serverupdated this year
An MCP server written in Golang to interact with the Ollama API
Apache-2.0 -
claude-token-saver-mcpgithub.com/BlackFoil/claude-token-saver-mcpupdated this year
MCP server that offloads coding tasks to local LLM (Ollama) to save Claude API tokens
npm Apache-2.0 ★ 3 -
An agent that takes booking calls for a diagnostic clinic: finds the exam, holds a slot, and hands over to a person with a named reason. A hundred scored golden calls gate CI; a second reader asks a local model through Ollama, measured on the same calls; an MCP server exposes the clinic as tools. No model or API key needed to run it.
MIT -
Local LLM deployment using Docker, Ollama and a custom MCP server with REST-based API integration.
-
it_asset_management_mcp_adk_chat_agentgithub.com/SudhakarC-hub/it_asset_management_mcp_adk_chat_agentupdated this year
Swagger API server + MCP Server + ADK + Streamlit chat app Ollama mistral self hosted
-
Cursor-history-MCPgithub.com/Nossim/Cursor-history-MCPupdated this year
API service to search vectorized Cursor IDE chat history using LanceDB and Ollama
★ 7 -
AI-powered VS Code extension that analyzes Figma designs using vision models (GPT-4o, Ollama) and automatically generates intelligent TypeSpec APIs with dual OpenAPI and MCP specifications.
MIT ★ 1 -
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 -
MESH-API — Off-Grid AI & API Router & with MCP server & over 30 API extensions for Meshtastic & MeshCore - Seamlessly connect LM Studio, Ollama, AI Providers , 3rd-party APIs, Agents & Home Assistant to your LoRa mesh. Supports custom commands, Twilio SMS, Discord channel routing, & GPS emergency alerts via SMS, email, or Discord + SO MUCH MORE
GPL-3.0 ★ 187 -
qdrant2github.com/neco001/qdrant2updated this year
Universal Qdrant MCP server with automatic dimension detection and search integrity. Supports any OpenAI-compatible embedding API (OpenAI, Qwen, Gemini, Ollama).
MIT -
MCP server for browser-use: browser automation in Cursor via stdio; LLM backend = local Cursor Agent CLI (agent) or OpenAI-compatible APIs (LM Studio, Ollama, etc.).
-
Local Blender MCP studio: bring your API, build, inspect and refine 3D scenes. Recommended starting points: GPT-6 Astra, Claude Opus/Sonnet, Gemini and Ollama. Visual feedback, approvals, CLI and demo.
MIT ★ 5 -
croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and enterprise data: an OpenAI-compatible LLM gateway, server-side agent execution, MCP, RAG, memory, sandbox, identity, RBAC and quotas. Routes across vLLM, SGLang, Ollama and hosted APIs.
AGPL-3.0 ★ 34 -
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
npm MIT ★ 3