AI & Machine Learning MCP Servers

MCP Azure server toolkit for dsh - cloud resources via Model Context Protocol. Name reserved; first release in development.

Security Proxy for Model Context Protocol — Govern any MCP tool call with ABS Core NRaaS (Non-Repudiation as a Service)

MCP Search server toolkit for dsh - web search via Model Context Protocol. Name reserved; first release in development.

MCP Server for Doktu telemedicine platform - enables AI assistants (ChatGPT, Claude) to discover doctors and book appointments

MCP server for Gemini 3 Nano Banana Pro image generation

MCP server for Fal AI image tools and Chatterbox TTS

MCP server for Alibaba Qwen3.7-plus vision model via DashScope Anthropic-compatible API

Model Context Protocol Framework - Fixed version with console-only logging

A Model Context Protocol (MCP) server for intelligent course content curation powered by GPT-4

MCP server for video analysis using Google Gemini and Moonshot Kimi AI

PolyCode CLI — one terminal agent for your own API keys across Anthropic, OpenAI, Gemini, DeepSeek, Mistral, xAI, Together, OpenRouter, Groq, Ollama + custom endpoints + MCP tools.

2026 最系统的 AI Agent 速成指南｜智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化

LightAgent: Lightweight AI agent framework with memory, mcp & skill. Supports multi-agent collaboration, self-learning, and major LLMs (OpenAI/DeepSeek/Qwen). Open-source with MCP/SSE protocol integration.

Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.

System of Record for Kubernetes cost accounting: per-namespace CPU, memory and GPU usage, with the 30% non-allocatable overhead made visible. Connects to AI assistants via MCP (Claude, Gemini, Mistral, Cursor) for plain-language analysis. Formerly Kube-Opex-Analytics.

Local LLM router. One endpoint for Claude Max/Pro, OpenAI, OpenRouter, Groq, Ollama, LiteLLM, any OpenAI-compat URL — your tools don't need to change. OAuth for Claude subscriptions, multi-account pool, MCP server. Zero runtime deps.

通用 AI 搜索 MCP 服务器，支持任何兼容 OpenAI API 格式的 AI 模型

MCP server for multi-round AI brainstorming debates across multiple models

No description available

Gemini 3.1 Flash Image MCP server - fast image generation with advanced reasoning, 512px-4K resolution, up to 14 reference images, Google Search grounding, and configurable thinking mode

MCP server for job search automation, auto apply, resume generation, application tracking, and recruiter outreach

Domain-specific LLM fine-tuning — sovereign models trained on your data, zero infrastructure.

Uncensored image, image-to-video and chat generation for adult apps. OpenAI-compatible, pay per use.

Toxicity, sentiment, NER, PII detection, and language identification tools