Google Gemini AI — generate content, embed text, count tokens, and run system-instructed completions.
Use with AI AssistantsMCP
Connect Claude, Cursor, or any MCP-compatible client — then call tools directly
① Add This MCP Server
Paste into your AI client config — then all its tools are available instantly.
{
"mcpServers": {
"gemini": {
"url": "https://mcp.aerostack.dev/s/aerostack/mcp-gemini",
"headers": {
"Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
}
}
}
}Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.
② Call a Tool
Ask your AI assistant to call a specific tool, or send raw JSON-RPC:
Natural Language Prompt
“Use the _ping tool to verify gemini credentials by calling a lightweight read endpoint. used internally by aerostack to validate credentials”
Using a Workspace?
Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.
Google Gemini AI — generate content, embed text, count tokens, and run system-instructed completions.
Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-gemini
This MCP server gives AI agents access to Gemini via 6 tools. Connect it to any Aerostack workspace and your agents can interact with Gemini directly.
| Tool | Description |
|---|---|
generate_content | Generate content using a Gemini model. Supports text generation with optional temperature and token controls. Default model is gemini-2.0-flash. |
list_models | List all available Gemini models with their capabilities, token limits, and supported generation methods. |
get_model | Get detailed information about a specific Gemini model including token limits and supported methods. |
count_tokens | Count the number of tokens in a prompt without generating a response. Useful for estimating costs. |
embed_content | Generate text embeddings using text-embedding-004 model. Returns a 768-dimensional embedding vector for semantic search, clustering, or similarity tasks. |
generate_with_system | Generate content with a system instruction that sets the model persona and context. More powerful than a regular system prompt in many use cases. |
| Variable | Required | Description |
|---|---|---|
GEMINI_API_KEY | Yes | Your GEMINI API KEY from the service's developer settings |
Add the following secrets under Project → Secrets:
GEMINI_API_KEYOnce added, every AI agent in your workspace can use Gemini tools automatically.
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-gemini \
-H 'Content-Type: application/json' \
-H 'X-Mcp-Secret-GEMINI-API-KEY: your-gemini-api-key' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"generate_content","arguments":{}}}'
MIT
Live Endpoint
https://mcp.aerostack.dev/s/aerostack/mcp-gemini
Sub-50ms globally · Zero cold start
@aerostack
Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.
by @aerostack
Design creation, AI generation, editing, export, assets, brand kits, folders via Canva's official MCP
by @aerostack
Conversations, contacts, tickets, articles via Intercom's official MCP
by @aerostack
Call Claude models directly — run AI conversations, tool-use chains, batch jobs, and model comparisons from any agent.
by @aerostack
Deployments, projects, domains, env vars, logs via Vercel's official MCP
by @aerostack
Read, send, and search Gmail messages — manage labels, drafts, and attachments with full inbox control.
by @aerostack
Manage audiences, campaigns, and subscriber tags in Mailchimp — automate your email marketing with AI.
The Gemini MCP gives Claude 6 tools covering contents, systems, models. Claude can read, create, update, and manage Gemini data directly from a conversation.
Yes. The Gemini MCP includes tools to list and retrieve models from your Gemini account. Claude can filter, sort, and summarize models based on your instructions.
Yes. The Gemini MCP uses the open Model Context Protocol standard, so it works in Claude, Cursor, Windsurf, and any other MCP-compatible AI tool. All 6 Gemini tools are available everywhere you connect it — install once on Aerostack.
The Gemini MCP exposes Gemini's AI capabilities to Claude — including generation, transcription, or embedding tools. Claude can chain these with other MCPs to build multi-step AI workflows.