Gemini MCP servers
MCP servers that connect an AI agent to Gemini: Gemini models, prompts and grounded generation. We have classified 189 so far, listed below and ranked by their independent trust score.
189 catalogued · how we score
Gemini at a glance
- Highest score
- 95 Code Lens
- Median score
- 72
- Scored
- 189 of 189
- Rescanned in 7 days
- 185
remote 111 · npm 70 · pypi 12 · mcpb 3 · oci 3 · figures as of 2026-09-20 13:30 UTC · how we score
Top 100 by trust score Trust score 0–100
- npm 95
Gemini-powered MCP server for code analysis.
- npm 92
io.github.chrischall/gemini-mcp
Generate and edit images with Google Gemini (Nano Banana / Nano Banana Pro) image models.
- npm 92
TokenLab MCP server: 31 default and 80 full-profile tools for models, media, tasks, and files.
- npm 91
Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs
- remote 91
Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
- remote 90
Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines.
- npm 90
Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.
- npm 90
AI memory across Claude, ChatGPT, Gemini, and Cursor. Save, search, and recall context everywhere.
- npm 89
Gemini-powered MCP server for code analysis.
- npm 88
Nano Banana MCP server — Google Gemini image generation and editing via Model Context Protocol
- remote · npm 87
LLM Audit deprecated
Measure whether AI assistants actually recommend a brand, from measured answers.
- remote 87
Scrape AI answer engines and Google Search/News with country and state-level geo-targeting.
- npm 87
Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.
- remote 87
Gemini Exchange keyless public market: symbols, ticker, candles, book, trades, price feed.
- npm 87
One MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.
- npm 86
io.github.Lykhoyda/ask-antigravity
Bridge Claude with Google's Antigravity CLI (agy) for code review and second opinions
- npm 86
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
- npm 85
Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
- remote 85
Pay-per-use AI and data tools via x402: image, video, music, voice, search, crypto. USDC.
- remote · npm 84
Measure whether AI assistants actually recommend a brand, from measured answers.
- npm 84
io.github.Daichi-Kudo/llm-advisor
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
- npm 84
AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents
- npm 84
io.github.philo-kim/openharness
Lets AI coding agents discover and reference each other's recent sessions.
- npm 84
io.github.PyModel/claude-agy-mcp
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
- npm 83
io.github.getjoystick/nanobanana-mcp
Lean MCP server for Google's Nano Banana (Gemini) image models. Returns file paths, not base64.
- remote · npm 83
Live status, API pricing and rate limits for ChatGPT, Claude, Gemini, Cursor and 42+ AI tools.
- npm 83
Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.
- npm 83
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
- npm 83
io.github.somacoffeekyoto/imgx
AI image generation and editing MCP server. Gemini + OpenAI, iterative editing, undo/redo.
- npm 83
io.github.sshahzaiib/agy-bridge
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
- npm 83
io.github.waqarulwahab/llm-cost-estimator
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
- npm 82
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
- npm 82
io.github.prateekg7/context-bridge
Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs.
- npm 82
io.github.runapi-builder/gemini-omni-mcp
RunAPI MCP server for Gemini Omni: create tasks, poll status, check pricing.
- npm 82
io.github.runapi-builder/gemini-tts-mcp
RunAPI MCP server for Gemini TTS: create tasks, poll status, check pricing.
- npm 82
io.github.spranab/brainstorm-mcp
Multi-model AI brainstorming debates with code review and quick perspectives
- npm 81
Asks 8 AI crawlers for your page, checks who really answered, and writes the fixes. MIT.
- npm 81
io.github.TheStevenJohnstone/ai-consensus
Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
- remote 80
Checks if AI assistants name a local business. Free shareable report, honest fixes, no guarantees.
- pypi 79
MCP server for Google Gemini AI - text, image, video, research, and more
- pypi 79
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
- remote · npm 79
AI-powered media & entertainment intelligence — research, briefs, and market data.
- remote 78
Specularis AI Visibility Audit
Free AI visibility (GEO/AEO) audit: can ChatGPT, Claude and Perplexity find and cite your website?
- remote 78
Signed exact-order pre-submit gate for crypto bots using live Coinbase and Gemini execution data.
- remote · npm 78
See how ChatGPT, Claude, Perplexity, and Gemini cite brands, prompts, and sources.
- remote 78
io.github.mikerawsonnz/authenticated-llm-agent
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
- remote 78
io.github.mikerawsonnz/authenticated-mcp-agent
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
- remote 78
io.github.mikerawsonnz/authenticated-multi-llm-agent
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f
- remote 78
io.github.mikerawsonnz/llm-observability-orchestration
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
- remote 78
io.github.mikerawsonnz/llm-orchestration-agent
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
- remote 78
io.github.mikerawsonnz/structured-output-agent
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Verte
- remote 78
io.github.mikerawsonnz/traced-llm-proxy
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t
- npm 78
x402 micropayment-powered developer tools: screenshots, AI analysis, PDFs, code scanning
- npm 78
io.github.raunakkathuria/lexilint
Offline spell checker + BYOK grammar for AI assistants. Works with Claude Desktop, ChatGPT, Cursor.
- npm 78
Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model
- remote · npm 77
See how ChatGPT, Claude, Gemini and Perplexity read any website. Scored out of 100.
- remote 77
io.github.AmauryDvl/serpmantics
French-first SEO: semantic content guides, scoring, E-E-A-T audits for Google, ChatGPT & Claude.
- remote 77
Alerts on breaking changes, deprecations, and pricing shifts across major LLM provider APIs.
- remote 77
io.github.omarkeshk/council-ai
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
- remote · npm 76
JarvisClaw — AI Gateway & API Marketplace
320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.
- remote 76
com.isitdeprecated/isitdeprecated
Check if an AI model is deprecated, retiring, or silently changed price or context window.
- remote 76
Swift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.
- pypi 76
Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.
- npm 76
io.github.vpatser1/ai-cost-analyzer
Analyze LLM API costs: token waste detection, caching savings estimates, model comparison
- npm 75
io.github.codeFi/mcp-nano-banana
MCP server for Google Nano Banana (Gemini) image generation
- remote 75
SEO + GEO tools in your AI editor: scan as ChatGPT and Google crawlers see it, fix order, llms.txt.
- remote 75
Consensus 'best X for Y' rankings from ChatGPT, Claude, Gemini & Grok. Search, verdicts, history.
- pypi 75
io.github.JoaoBerne/cli-bridge-mcp
Other AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.
- npm 75
io.github.RudrenduPaul/truthroute
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
- npm 75
Autopilot AI orchestration — auto-plan, parallelize, self-heal, and route across 6 LLMs.
- remote 74
Agent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.
- remote 72
ai.getvda/authenticated-llm-agent
Authenticated LLM Agent
- remote 72
ai.getvda/authenticated-llm-agent-bcrypt
Authenticated LLM Agent (Bcrypt)
- remote 72
ai.getvda/authenticated-llm-jwt-agent
Authenticated LLM JWT Agent
- remote 72
ai.getvda/authenticated-llm-mcp-agent
Authenticated LLM MCP Agent
- remote 72
ai.getvda/authenticated-llm-traced-agent
Authenticated LLM Traced Agent
- remote 72
ai.getvda/authenticated-mcp-agent-aed9d5
Authenticated MCP Agent
- remote 72
ai.getvda/authenticated-mcp-agent-bcrypt
Authenticated MCP Agent (Bcrypt)
- remote 72
ai.getvda/authenticated-mcp-agent-openai
Authenticated MCP Agent (Openai)
- remote 72
ai.getvda/authenticated-mcp-traced-agent
Authenticated MCP Traced Agent
- remote 72
ai.getvda/authenticated-multi-llm-agent
Authenticated Multi-LLM Agent
- remote 72
ai.getvda/claude-schema-output-agent
Claude Schema Output Agent
- remote 72
ai.getvda/encrypted-langchain-session-agent
Encrypted LangChain Session Agent
- remote 72
ai.getvda/encrypted-langchain-token-agent
Encrypted LangChain Token Agent
- remote 72
ai.getvda/encrypted-oauth-llm-agent
Encrypted OAuth LLM Agent
- remote 72
ai.getvda/google-oauth-credential-service
Google OAuth Credential Service
- remote 72
ai.getvda/google-oauth-langchain-agent
Google OAuth LangChain Agent
- remote 72
ai.getvda/google-sign-in-claude-agent
Google Sign-In Claude Agent
- remote 72
ai.getvda/google-sign-in-langchain-agent
Google Sign-In LangChain Agent
- remote 72
ai.getvda/langchain-login-and-token-agent
LangChain Login and Token Agent
- remote 72
ai.getvda/llm-observability-orchestration
LLM Observability & Orchestration Agent
- remote 72
ai.getvda/llm-observability-orchestration-agent-langchain
LLM Observability & Orchestration Agent (Langchain)
- remote 72
ai.getvda/llm-observability-orchestration-agent-langchain-community
LLM Observability & Orchestration Agent (LangChain Community)
- remote 72
ai.getvda/llm-orchestration-agent-2
MCP-Native LLM Orchestration Agent
- remote 72
ai.getvda/llm-orchestration-agent-2-df5979
LLM Orchestration Agent 2
- remote 72
ai.getvda/llm-orchestration-agent-cryptography
LLM Orchestration Agent (Cryptography)
- remote 72
ai.getvda/llm-orchestration-agent-d0a1a1
LLM Orchestration Agent
- remote 72
ai.getvda/llm-orchestration-agent-d2feb0
LangSmith-Traced LLM Orchestration Agent
- remote 72
ai.getvda/llm-orchestration-agent-langchain
LLM Orchestration Agent (Langchain)
- remote 72
ai.getvda/llm-orchestration-agent-langchain-anthropic
LLM Orchestration Agent (Langchain Anthropic)
Every server here has been scored. A server is listed here because its description and tool definitions say it is built for Gemini. That is what the server declares about itself, not an integration we have tested, so check the score breakdown before you trust one. This classification currently runs only over servers that publish a hosted endpoint, so a Gemini server distributed solely as an installable package will not appear here yet, however clearly it belongs. Treat the ranking as a partial field rather than the whole one.
Common questions
What is a Gemini MCP server?
A Gemini MCP server exposes Gemini models, prompts and grounded generation to an AI assistant over the Model Context Protocol, so the assistant can work with Gemini directly instead of you moving data in and out by hand. These come from the public MCP registry, and being listed there is not a review of the code, so the publisher is worth checking as closely as the feature list.
How do I get started with a Gemini MCP server?
Start from the ranked list on this page, then open a server's own page and read its score breakdown before you install anything. Every server listed here is a hosted endpoint, so that breakdown covers Endpoint Security, Transport & Reachability, Schema Quality & AI Usability, Stability & Change Management, Tool Coverage, Tool Safety and Capabilities. A Gemini server acts on your Gemini data, so check what access it asks for before you connect it. The same page carries install snippets for the common MCP clients.