Access Google Gemini's 30+ capabilities—image generation, video processing, research, text-to-speech, code execution, and CLI tools—directly from your AI chat. For developers building AI workflows that need multimodal content creation and analysis.
io.github.RLabs-Inc/gemini-mcp
Local install
STDIO
1 required env var
How models use it and what it is built for.
Access Google Gemini's 30+ capabilities—image generation, video processing, research, text-to-speech, code execution, and CLI tools—directly from your AI chat. For developers building AI workflows that need multimodal content creation and analysis.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Your Google Gemini API key (get one at https://aistudio.google.com/apikey)
Directory for generated files (images, videos, audio)
Where to find authoritative docs and source for Rlabs Inc Gemini.
Paste any of these into Agent Studio after connecting Rlabs Inc Gemini.
Common questions about connecting and running Rlabs Inc Gemini.
How do I set up the Gemini MCP server?
Install via `npx @rlabs-inc/gemini-mcp@0.7.1`, then set the required `GEMINI_API_KEY` environment variable (get a free key at https://aistudio.google.com/apikey). Optionally set `GEMINI_OUTPUT_DIR` to specify where generated files (images, videos, audio) are saved.
What are the main capabilities of this server?
The server exposes 30+ Gemini tools including image generation, video processing, research, text-to-speech, code execution, and CLI operations. You can chain these tools together in a single conversation to build complex multimodal workflows.
Is there a cost to use this MCP server?
You need a Google Gemini API key (free tier available at https://aistudio.google.com/apikey). Pricing depends on your Gemini API usage; check Google's pricing page for current rates on image generation, video processing, and other features.
Where do generated images, videos, and audio files get saved?
By default, files are saved to a system temp directory. Set the `GEMINI_OUTPUT_DIR` environment variable to specify a custom output directory for all generated content.
Can I execute arbitrary code with this server?
Yes, the server includes code execution tools, but always review and validate generated code before running it. Use the CLI tools cautiously in production environments and follow your organization's security policies.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams