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.
-
gpt-4o-search-mcpgithub.com/jedarden/gpt-4o-search-mcpupdated this year
gpt-4o-search as a MCP server
MIT ★ 2 -
RunAPI GPT-4o Image MCP server for image generation: create tasks, poll results, and check pricing across 1 model from Claude Code, Codex, Cursor, and VS Code.
npm Apache-2.0 -
A Streamlit-based chatbot interface powered by OpenAI GPT-4o that intelligently routes user input to custom MCP tools such as GPT chat, image generation, Supabase queries, and text-to-speech.
★ 2 -
MCP server that analyzes images and provides structured metadata for website placement decisions using OpenAI GPT-4o Vision API
npm MIT -
LLM-Router-MCPgithub.com/Devatva24/LLM-Router-MCPupdated this year
MCP server that intelligently routes prompts across Claude, Gemini, and GPT-4o based on task type — minimising token cost without sacrificing quality.
npm -
llm-arena-mcpgithub.com/snowbikemike/llm-arena-mcpupdated this year
Multi-LLM MCP Server — Route prompts to GPT-4o, Claude, Gemini, Grok, Llama, and Mistral simultaneously. Compare responses side-by-side with automated behavioral pattern detection.
npm MIT -
Multi-agent travel planner on LangGraph and GPT-4o: a root agent routes each request to 3 specialist agents with live flight, hotel and places data, plus a weather MCP server.
MIT ★ 1 -
Bilingual (English-Arabic) realtime voice AI agent for LiveKit using Azure Speech STT/TTS, GPT-4o-mini, and a FastMCP HTTP server for tool calling.
★ 1 -
Optimizador de imágenes web de alto rendimiento, 100% Serverless. Compresión inteligente sin pérdida, super-resolución Lanczos3, formato Historias 9:16 con blur, suite de favicons, IA Vision SEO (Gemini/GPT-4o) y compatibilidad nativa con Agentes Autónomos (MCP, ARD, OpenAPI).
MIT -
Hallucination guardrail for AI output about indexed documents. POST a claim, get PASS or FAIL with the exact source passage, checked by a Researcher + Critic LangGraph pipeline (LangChain, Pinecone, GPT-4o). FastAPI service on Render, plus an MCP server, Streamlit UI and eval harness.
MIT -
🤖 AI-powered ghostwriting system with GPT-4o integration and MCP architecture - 代筆さん AI統合版
★ 1 -
It can make mcp client interact with openai api. you can use openai model gpt-4.5-preview, o3-mini, o1, gpt-4o
MIT ★ 1 -
vision-mcp-servergithub.com/Loveacup/vision-mcp-serverupdated this year
MCP server providing multimodal vision capabilities via OpenAI-compatible API (Qwen3-VL, GPT-4o, etc.)
MIT ★ 20 -
openai-mcpgithub.com/1Aa1k/openai-mcpupdated this year
Tiny MCP server that proxies any OpenAI chat-completion model ID (GPT-5.5, GPT-4o, o1, etc.) to OpenAI without a local whitelist.
MIT -
An end-to-end AI-powered FAQ assistant that uses vector semantic search in Azure SQL Hyperscale, Retrieval-Augmented Generation (RAG) with GPT-4o, and Model Context Protocol (MCP) to ground AI responses in approved support content, with no hallucinations.
MIT ★ 3 -
TalkToYourLogServergithub.com/ibranibeny/TalkToYourLogServerupdated this year
Contoso PoC - Talk to Your Data Logs with Azure AI. Hybrid cloud architecture with MCP Server, Azure AI Search, AI Foundry (GPT-4o), Elasticsearch, and Streamlit frontend.
★ 1 -
nanolensupdated this year
CLI + MCP tool for image analysis — ZAI (GLM-4.6V), Kimi (K2.5), GitHub Copilot (gpt-4o), Alibaba (Qwen3.5)
npm MIT -
Sample MCP Server on Azure that lists images from Blob Storage and describes them using Azure OpenAI (gpt-4o vision).
★ 6 -
hotel-voice-receptionistgithub.com/ShreHari/hotel-voice-receptionistupdated this year
AI voice receptionist with an agentic loop and real MCP tools. FastAPI, gpt-4o-mini, Web Speech API, SQLite, Docker.
-
vision-toolkitgithub.com/leiming2333/vision-toolkitupdated this year
多模态视觉 MCP + 文生图 Skill 工具包 (OpenAI GPT-4o · 通义千问 Qwen-VL · Google Gemini · Anthropic Claude)
npm MIT -
vision-mcpgithub.com/Skirja/vision-mcpupdated this year
MCP server that adds visual understanding capabilities to text-only coding models. Supports OpenAI GPT-4o and compatible vision APIs.
-
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 -
AI-powered e-commerce search agent that simultaneously scans 11+ platforms (Amazon, eBay, Walmart, etc.) for intelligent product discovery, price comparison, and deal analysis using GPT-4o
MIT ★ 2 -
Hybrid RAG + MCP medical dialogue system (Master's thesis). Risk detection 87.5% vs GPT-4o 37.5%.
MIT -
kiragithub.com/Ogeanni/kiraactive
Production RAG pipeline + multi-agent system for e-commerce analytics. Embeddings · Pinecone · MCP · GPT-4o-mini · Anomaly detection · FastAPI · Deployed on Render
-
regulations-mcpgithub.com/stark256-spec/regulations-mcpupdated this year
MCP server for live U.S. federal regulations — Federal Register, eCFR, Regulations.gov. Works with any LLM (Claude, GPT-4o, Gemini, Mistral, Llama, Ollama).
pypi ★ 1 -
llm-cost-estimator-mcpgithub.com/waqarulwahab/llm-cost-estimatorupdated this year
MCP server for LLM token counting and multi-model cost estimation (GPT-4o, Claude, Gemini, and 25+ models). Local-first, no API key.
npm MIT -
conductorgithub.com/useconductor/conductorupdated this year
AI integration hub — 25 plugins, 146 tools. Connect Claude, GPT-4o, Gemini & Ollama to Gmail, Spotify, GitHub Actions, Vercel, n8n, Notion and more. One installer. MCP + Telegram.
Apache-2.0 ★ 2 -
Basic reusable MCP Server local setup, with gpt-4o agent connection, tool calling, and local file writing.
-
image-vision-mcpgithub.com/staticdeng/image-vision-mcpupdated this year
Multi-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.
npm MIT -
image-tiler-mcp-servergithub.com/keiver/image-tiler-mcp-serverupdated this year
MCP server that prevents LLM vision downscaling, tiles large images & screenshots so Claude, GPT-4o, and Gemini see every detail
npm MIT ★ 3 -
Vacanzagithub.com/davids199005-oss/Vacanzaupdated this year
Full-stack travel platform — vacation booking, AI recommendations via GPT-4o-mini, MCP server, admin panel with charts & CSV export. React 19 + Express 5 + MySQL + Docker
MIT ★ 1 -
wooden-vision-mcpactive
A generic MCP server that lets a text-only LLM agent 'see' images by sending them to any OpenAI-compatible multimodal model (e.g. gpt-4o, glm-4.6v, qwen-vl).
npm MIT -
ckg-mcpgithub.com/yarmoluk/ckg-mcpupdated this year
Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.
pypi MIT -
Fable 5.1 Multi-Agent Architect & Invariant Verification Gate for Claude Code, Cursor & Web. Decouples task contracts from worker subagents with adversarial failure injection testing. BYOK (Claude 3.7, GPT-4o, DeepSeek, Ollama).
MIT ★ 1 -
ai-driven-multimodal-analyticsgithub.com/serhatsoysal/ai-driven-multimodal-analyticsupdated this year
Enterprise-grade Multimodal AI Gateway leveraging FastAPI, OpenAI (GPT-4o, Whisper, TTS), and MCP Server architecture. Featuring asynchronous task processing, Redis caching, and real-time AI/ML pipeline orchestration.
MIT ★ 1 -
Aadvanced-MCP-Labgithub.com/LeelaissakAttota/Aadvanced-MCP-Labupdated this year
Advanced MCP implementation with remote HTTP transport, filesystem roots security, server-initiated LLM sampling & OpenAI GPT-4o-mini integration — production-ready agentic AI architecture
★ 1 -
AIproject-portfoliogithub.com/KirillTomenko/AIproject-portfolioupdated this year
- FastAPI MCP server with 7 tools (projects, stats, post ideas, generate post) - aiogram 3.x bot with OpenAI GPT-4o-mini via ProxyAPI - SQLite database seeded with real portfolio projects - Docker support (Dockerfile + docker-compose)
-
An LLM eval harness graded by computed ground truth, not an LLM judge. Worked example: poker, served to models as MCP tools — gpt-4o-mini goes from 26/75 to 75/75 with them.
MIT ★ 1 -
mcp-weather-israelgithub.com/leah-git1/mcp-weather-israelupdated this year
MCP server that uses Playwright to automate a real browser and fetch live weather forecasts from an Israeli weather site. Also supports US weather via the NWS API — powered by OpenAI gpt-4o-mini
★ 2 -
agentic-test-generatorgithub.com/Hrushitha12/agentic-test-generatorupdated this year
5-agent AI system using CrewAI, MCP, and A2A Protocol to autonomously generate API test suites from OpenAPI specs — GPT-4o/Claude Sonnet via LiteLLM with LangSmith tracing
-
now-ai-kitgithub.com/habenani-p/servicenow-mcpupdated this year
The most advanced & comprehensive ServiceNow MCP server — 150+ tools across 17 modules, full ServiceNow API coverage, integrates with Claude, GPT-4o, Gemini, Cursor, VS Code, and Codex
npm MIT -
seo-ai-agentgithub.com/SimplerSoftwareIO/seo-ai-agentupdated this year
A production-ready Python SEO agent that connects GPT-4o, Google Search Console, Google Analytics 4, FireCrawl and DataForSEO into a single autonomous loop - with persistent memory, a Streamlit dashboard, and a VS Code MCP server so GitHub Copilot can run SEO queries directly from your editor.
MIT ★ 3 -
Andrea---AI-Healthcare-Receptionistgithub.com/ShreyKamdar0503/Andrea---AI-Healthcare-Receptionistupdated this year
Andrea is a production-ready, multi-agent voice AI receptionist for a dental clinic, built using VAPI, GPT-4o-mini, n8n workflows, and an MCP server. It handles real-world phone conversations including appointment scheduling, intake, insurance checks, and call logging with low latency and high reliability.
-
Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.
npm Apache-2.0 ★ 55 -
AI-Tutor-MCP-Toolkitgithub.com/alhadbhadekar/AI-Tutor-MCP-Toolkitupdated this year
The AI Tutor MCP Toolkit is a compact, multi‑tool server built with Gradio and powered by OpenAI's GPT‑4o‑mini model. It exposes four learning‑oriented tools via the Model‑Context‑Protocol (MCP) and provides both a web UI and an MCP‑enabled agent for interactive educational tasks.
-
Universal Cybersecurity Model Context Protocol (MCP) Server & Token-Saving Agent Skills for Claude Desktop, Cursor, GPT-4o, and Antigravity. Purple Teaming, WAF Triad Audit, Malware PE Triage, USB Forensics & Caveman Token Optimizer.
MIT -
Wazuh-MCP-Servergithub.com/ArfanAbid/Wazuh-MCP-Serverupdated this year
Connect LLMs (Claude, GPT-4o) to your Wazuh SIEM via MCP, natural-language queries for live alerts, agents, rules, compliance, system inventory & security infrastructure, backed by Wazuh Manager and OpenSearch Indexer, with REST API endpoints and a custom Next.js frontend.
★ 1 -
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
AGPL-3.0 ★ 83 -
Autonomous cyber red team intelligence for AI agents — this MCP server gives Claude, GPT-4o, and any MCP-compatible agent the ability to run quantitative attack simulations, synthesize exploit chains, forecast vulnerability emergence, and model adversary behavior using eight rigorously implemented mathematical frameworks.
MIT ★ 1 -
Turn a plain-English request ("compare Apple and Microsoft YTD") into a validated stock chart — a CrewAI multi-agent pipeline exposed as MCP tools for Claude Desktop/Code, using yfinance data, AST-validated code generation, and sandboxed execution. Runs on local (Ollama/DeepSeek-R1) or cloud (Groq, GPT-4o) LLMs.
MIT -
sight-mcpstale
MCP server for AI-powered image and video analysis - supports OpenAI, Claude, and multimodal vision APIs with local file and URL processing
npm MIT -
@atercates/vision-judgeupdated this year
MCP server and CLI tool for web design critique using GitHub Copilot vision
npm MIT -
MCP Server wrapper for TTS engines (Kokoro TTS and OpenAI TTS)
NOASSERTION ★ 7 -
@haisto/vision-mcpgithub.com/haisto/vision-mcpupdated this year
Multi-model vision understanding MCP server. Supports OpenAI-compatible and Anthropic vision models.
npm MIT -
MCP server for secure, bounded OpenAI-compatible vision analysis
npm MIT -
MCP server for image generation via Chat Completion API using OpenAI-compatible APIs
npm MIT -
Unified MCP server for multimodal media: Higgsfield video (Seedance, Kling), OpenAI images, speech and transcription, ElevenLabs podcasts
pypi MIT -
Model Context Protocol server for the expanded Kie.ai image and video generation APIs
npm MIT -
Vision models pay for tiles, not megapixels. Per-provider token math, exact + budget resize, zero-dep PNG/JPEG codecs, Claude Code hook, MCP server.
npm MIT