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.
-
gemini-3-pro-image-mcpgithub.com/kiyo-e/gemini-3-pro-image-mcpupdated this year
—
MIT -
gemini-3-online-mcpgithub.com/rocnubie/gemini-3-online-mcpupdated this year
Gemini 3 Online is a web-based AI creative platform built around Google's Gemini Pro models and Veo 3 video generation technology. It gives users access to a suite of image and video creation tools directly in the browser, without requiring local setup or specialized hardware.
MIT -
ultimate-gemini-mcpgithub.com/anand-92/ultimate-image-gen-mcpupdated this year
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
pypi MIT -
Ultimate Gemini 3.1 Flash Image MCP server with 4K generation, Google Search grounding, reference images (up to 14), and thinking mode. Professional image generation made simple.
NOASSERTION ★ 14 -
High-performance Model Context Protocol (MCP) server connecting Claude Code and AI agents to Google Gemini 3.8 Flash, Gemini 3.1 Pro, reasoning effort, and image generation.
npm MIT -
fcp-gemini-servergithub.com/Food-Context-Protocol/fcp-gemini-serverupdated this year
Reference Gemini 3-powered Python/FastAPI implementation with 40+ MCP tools
Apache-2.0 -
claude-gemini-bridgegithub.com/archolet/claude-gemini-bridgeupdated this year
Claude Code icin Vertex AI uzerinden Gemini 3 modellerine erisim saglayan MCP sunucusu
MIT -
gemini_mcp_onekeygithub.com/aiagenta2z/gemini_mcp_onekeyupdated this year
Gemini API (Gemini 3, Gemini 2.5, Nano Banana)MCP Server & DeepNLP OneKey MCP Router Support
★ 2 -
@dondonudonjp/nanobanana-mcp-serverupdated this year
MCP server for Google Gemini NanoBanana (2.5 Flash Image, 3 Pro Image, 3.1 Flash Image & 3.1 Flash Lite Image) AI image generation and editing
npm MIT -
gemini-design-mcpupdated this year
MCP server that uses Gemini 3 Pro for frontend/design code generation
npm MIT -
MCP tool plugin for Magpie exposing Nano Banana 2.1, Gemini Files API, and 3.8 TTS
MIT -
@lkbaba/mcp-server-geminigithub.com/lkbaba/gemini-mcpupdated this year
MCP server for Gemini 3.1 Pro focused on UI generation and frontend development
npm MIT -
andrew-nanobanana-mcp-servergithub.com/nano-banana/mcp-serverupdated this year
A production-ready MCP server for AI-powered image generation using Gemini 3.1 Flash Image (Nano Banana 2, default), Gemini 3 Pro Image, and Gemini 2.5 Flash Image with intelligent model selection
pypi MIT -
atlascloud-mcpactive
MCP server for AI image / video / 3D / audio (TTS, music, speech-to-text) generation & LLM chat. Use Sora 2, Veo 3, Kling 3, Seedance 2, Flux 2, Nano Banana Pro, Hunyuan 3D, Seed Audio, Suno in Claude Code, Cursor, Codex, Gemini CLI.
npm MIT -
gemini-studio-mcpgithub.com/arterorx/gemini-studio-mcpupdated this year
MCP server for iterative image & video generation via the Gemini API (Imagen 4, Gemini 3 Pro Image, Veo) — generate and refine in plain words, inside Claude.
MIT -
Estudio privado de producción con IA sobre Google Vertex AI: Nano Banana, Veo 3.1, Gemini Omni, Lyria 3, motion graphics por código y un director autónomo con MCP.
MIT -
video-generatorgithub.com/stephenpadgett1/video-generatorupdated this year
AI video production workflow: Veo 3.1 + Gemini 3 Pro Image + ElevenLabs orchestrated via an MCP server, with Claude-vision QA loops for materializing props, ghost limbs, and flicker.
-
@ariesli/deepseek-vision-mcpgithub.com/arieslee/deepseek-vision-mcpupdated this year
MCP server that calls the Gemini vision model (default gemini-3.5-flash) to analyze images.
npm MIT -
A Model Context Protocol (MCP) server that provides a prompt optimization service for Large Language Models (LLMs) using Google Gemini, with advanced prompt engineering thanks to 22365_3_Prompt_Engineering_v7.pdf authored by Lee Boonstra
npm MIT -
Local-first memory backend for AI agents · 99.2% LongMemEval-S retrieval @ k=8 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable
pypi Apache-2.0 ★ 31 -
githubAnalysergithub.com/HarrisWarner04/githubAnalyserupdated this year
Intelligent Model Context Protocol (MCP) server that analyzes GitHub repositories against industry standards using Gemini 3.5 & Groq LLaMA 3.1. Supports stdio & Streamable HTTP for local clients (Claude Desktop/Cursor) and remote VM deployment.
-
Plan, generate, compose, and edit images and video with Gemini image models, Veo 3.1, and Gemini Omni, with a cost estimate before every call and an optional Gemini 4 Argon director that checks each take against your notes.
pypi Apache-2.0 ★ 1 -
@justmpm/nanobananaupdated this year
MCP Server for AI image generation using Google Gemini 3.1 Flash Image (NanoBanana)
npm MIT -
ComfyUI workflows and GPU LoRA training in Gemini CLI. AI image models FLUX 2 and Seedream 5.0; AI video models Seedance 2.5, Wan 3.0, Wan 2.2 and LTX 2.5.
MIT -
openrouter-image-mcp-serverupdated this year
MCP server for image generation via OpenRouter (Nanobanana 2 / Gemini 3.1 Flash Image)
npm -
nano-banana-pro-mcpupdated this year
MCP server for 4K image generation using Gemini 3 Pro Image with advanced features
npm MIT -
gemini-creative-plugingithub.com/2901were/gemini-creative-pluginupdated this year
Gemini Creative — Claude Code plugin wrapping a Model Context Protocol server for AI image generation via Google's Gemini 3 image models. Sessions-first API with 9 auto-activating skills for game art, UI mockups, character sprites, and prompt engineering.
MIT ★ 1 -
nano-banana-mcpgithub.com/slavinjo/nano-banana-mcpupdated this year
Simple NanoBanana MCP supporting 'gemini-2.5-flash-image' and 'gemini-3-pro-image-preview'
-
FastMCP 3.2 gateway for Google AI: Gemini chat, Nano Banana images, Veo video, Gemini Omni multimodal, Lyria music, TTS, embeddings — with React dashboard and Docker.
MIT ★ 2 -
为 Codex 主模型配备 Antigravity Gemini 3.8 Flash (High) 子代理集群:在不损失主模型能力的前提下节约 token,用上 Google AI Pro 闲置额度(仅针对 Codex 优化)
MIT -
mcpstore-nano-bananaupdated this year
MCP server for AI image generation, editing, composition and style transfer using Google Gemini 3 Pro Image (Nano Banana Pro)
npm MIT -
codebase-analyzer-mcpgithub.com/jaykaycodes/codebase-analyzer-mcpupdated this year
Multi-layer codebase analysis with Gemini AI. 4 agents, 5 commands, 3 skills for architecture analysis, pattern detection, and dataflow tracing
npm MIT ★ 3 -
@lel190/mcp-lel190-imageupdated this year
MCP server for image generation using Gemini 3.1 Flash Image (Nano Banana 2) via api.lel190.dev
npm MIT -
MCP server bridging Claude with Google Gemini (Gemini 4 Argon, Omni Flash video, Nano Banana images, Lyria music, 3.8 TTS, Deep Research, Antigravity agent, 1M context) and 400+ OpenRouter models. 28 tools, models auto-detected.
pypi MIT ★ 12 -
AI-powered content and image generation with Google Imagen 3/4, Veo 3, and Gemini 2.0 Flash
MIT -
A local FastMCP server that lets **Flash 3.8** act as the primary Antigravity orchestrator while calling **Gemini 4 Argon** (`gemini-4-argon`) via the Google GenAI API (billed against AI Studio / Google Developer Program credits).
-
nanobanana-pro-mcp-servergithub.com/qso/nanobanana-mcp-serverupdated this year
A production-ready MCP server for AI-powered image generation using Gemini 3 Pro Image (Nano Banana Pro) and Gemini 2.5 Flash Image with intelligent model selection
pypi MIT -
Token-saving Cyrillic markdown translation layer for Antigravity (agy): fast Gemini 3.7 Flash translate tier, lazy EN doc cache via PreToolUse hook, AGENTS.md / GEMINI.md sync, MCP and skills
npm MIT -
High-performance Pure Python MCP Server & Dual-Mode CLI connecting Claude Code, Cursor, and Codex to Google Antigravity (Gemini 3.8 Flash / Pro)
MIT -
A 3-minute AI briefing written every weekday by an AI agent, with every fact checked against its source. MCP server + Gemini agent + guardrails.
-
Model Context Protocol (MCP) server that lets Claude Code generate images (Imagen 4) and videos (Veo 3.1) via the Gemini API, straight into your project.
pypi MIT ★ 2 -
Let Claude Code, Codex, Cursor & Gemini CLI make images and videos in your own Google Flow tab (Veo 3.1, Nano Banana). Claude Code plugin + Gemini CLI extension.
MIT -
comfyui_LLM_partyygithub.com/heshengta0/comfyui_LLM_partyyupdated this year
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
AGPL-3.0 ★ 2 -
comfyui_LLM_partygithub.com/heshengta0/comfyui_LLM_partyupdated this year
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
AGPL-3.0 ★ 2 -
comfyui_LLM_partygithub.com/heshengtao/comfyui_LLM_partyupdated this year
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
AGPL-3.0 ★ 2,390 -
image-generation-mcpgithub.com/davoodwadi/image-generation-mcpupdated this year
MCP server for generating images using Gemini 3 Pro
-
google-live-translategithub.com/sergiocalvog/google-live-translateupdated this year
Apify Actor & MCP Server for real-time translation, transcription, and language detection using Google Gemini 3.5 Live Translate with emotional voice preservation.
★ 1 -
apac-genaiacademygithub.com/divyamohan1993/apac-genaiacademyupdated this year
Gen AI Academy APAC Edition — 3 production AI solutions: FirstResponse AI (emergency triage), AgroAdvisor (smart farming), EduPulse (student analytics) | ADK + Gemini + MCP + AlloyDB + Cloud Run
-
spatial-opticiangithub.com/vero-code/spatial-opticianupdated this year
AI-powered facility lighting audit and ROI optimization platform. Powered by Gemini 3.5, Google ADK, MCP & MongoDB. Supported by MongoDB for Startups.
MIT -
MCP server for Antigravity Claude Proxy — use Claude Opus 4.6, Sonnet 4.6, and Gemini 3 via any MCP client. TypeScript, tested, zero-config.
npm MIT -
A production-ready Salesforce integration platform unifying Gemini 3.6 Flash AI, Slack Socket Mode, Gmail, Google Calendar, and Snowflake through Model Context Protocol (MCP).
-
nano-banana-mcp-g3github.com/mascotbot/nano-banana-mcpupdated this year
MCP server for Google's Gemini 3 Pro Image generation API with 4K output, aspect ratio control, Google Search grounding, conversational editing, and image description/analysis
npm MIT -
antigravity-claude-mcpgithub.com/arjunthilak05/antigravity-claude-mcpupdated this year
Give Claude Code a second brain: ask Google Antigravity (Gemini 3 Pro, Claude, GPT-OSS) for an independent code review / second opinion via MCP. One command, zero deps.
npm MIT ★ 3 -
antigravity-claude-mcpgithub.com/arjunthilakeros/antigravity-claude-mcpupdated this year
Give Claude Code a second brain: ask Google Antigravity (Gemini 3 Pro, Claude, GPT-OSS) for an independent code review / second opinion via MCP. One command, zero deps.
MIT -
Google AI Studio inside Claude — Gemini, Nano Banana images, Veo 3.1 video with audio, and TTS as a zero-dependency MCP server, with a mocked end-to-end test suite
MIT -
nano-banana-pro-mcpgithub.com/mrafaeldie12/nano-banana-pro-mcpupdated this year
MCP server for Gemini 3 Nano Banana Pro image generation
npm ★ 17 -
gitlab-code-review-mcpgithub.com/Trojan0523/gitlab-code-review-mcpupdated this year
A reviewing MCP tool, vibe coding by gemini 3.0
MIT -
MCP server for AI image generation via laozhang.ai Gemini 3 Pro API
★ 2 -
multi-agent-it-ops-deskgithub.com/Rudra7777/multi-agent-it-ops-deskupdated this year
Governed multi-agent IT operations desk — LangGraph orchestration + 3 MCP servers (custom Directory & Access, Zapier, vectorless Policy KB RAG) with human-in-the-loop approval gates, on Gemini/Vertex AI
-
FlashCardCreatorgithub.com/kschmidt1144/FlashCardCreatorupdated this year
AI flashcard + mock-interview deck generator: upload a PDF/DOCX or paste text, and a Gemini-driven backend writes Q/A cards stored per-user in Firestore. Features a hand-built Gemini tool-calling loop and a Model Context Protocol (MCP) server that lets Claude create and manage decks against the live backend. FastAPI + Vue 3 PWA.