KosmoKrator

ai

Google Gemini MCP Integration for OpenAI Agents SDK

Connect Google Gemini to OpenAI Agents SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 6 read 1 write API key auth
Submit Google Gemini feedback View package source

Connect Google Gemini to OpenAI Agents SDK

Attach KosmoKrator integration tools to OpenAI Agents SDK workflows through a local MCP gateway.

Start the KosmoKrator MCP gateway locally and point the OpenAI Agents SDK MCP tool at that process or wrapper. The gateway is local, scoped to this integration, and starts with --write=deny so OpenAI Agents can inspect read-capable tools without receiving write access by default.

Google Gemini MCP Config for OpenAI Agents SDK

Use headless JSON commands for CI-style execution and MCP for agent tool discovery.

{
  "mcpServers": {
    "kosmokrator-google-gemini": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=google-gemini",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=google-gemini --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Google Gemini instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Google Gemini Tools Visible to OpenAI Agents

OpenAI Agents sees stable MCP tool names generated from the Google Gemini integration catalog.

MCP toolSource functionTypeDescription
integration__google_gemini__gemini_list_models google-gemini.gemini_list_models Read List available Gemini AI models. Returns model names, display names, supported generation methods, and other metadata.
integration__google_gemini__gemini_get_model google-gemini.gemini_get_model Read Get detailed information about a specific Gemini model, including supported generation methods, input/output token limits, and capabilities.
integration__google_gemini__gemini_generate_content google-gemini.gemini_generate_content Write Generate content using a Gemini model. Send text prompts and receive AI-generated responses. Supports configurable generation parameters like temperature, topP, and maxOutputTokens.
integration__google_gemini__gemini_list_files google-gemini.gemini_list_files Read List files uploaded to the Gemini File API. Returns file names, MIME types, sizes, and states.
integration__google_gemini__gemini_get_file google-gemini.gemini_get_file Read Get metadata for an uploaded file in the Gemini File API, including its name, display name, MIME type, size, and processing state.
integration__google_gemini__gemini_list_tuned_models google-gemini.gemini_list_tuned_models Read List tuned (fine-tuned) Gemini models in your project. Returns model names, base models, tuning tasks, and display names.
integration__google_gemini__gemini_get_current_user google-gemini.gemini_get_current_user Read Get information about the currently authenticated Google user, including permissions and account details.

Related Google Gemini Pages

Google Gemini CLIUse direct JSON commands instead of MCP discovery. Google Gemini MCPFull gateway reference and MCP tool names. KosmoKrator for OpenAI AgentsClient-level gateway setup.