Can I use Google Gemini as a CLI?

Yes. KosmoKrator exposes a Google Gemini CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Google Gemini through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Google Gemini tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Google Gemini credentials stored?

Google Gemini credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Google Gemini MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

Google Gemini MCP, CLI, and Lua Integration for AI Agents

Google Gemini integration docs for AI agents: MCP gateway setup, Google Gemini CLI commands, Lua API reference, credentials, and function schemas.

7 functions 6 read 1 write API key auth

Submit Google Gemini feedback View package source

Google Gemini for agents

Credentials can be configured manually in web or CLI hosts.

Use this integration from Lua code mode, the headless integrations CLI, or the KosmoKrator MCP gateway. The same package metadata powers all three surfaces.

Machine-Readable Metadata

integration_slug: google-gemini
route_slug: google-gemini
package: google-gemini
auth_strategy: api_key API key
cli_setup_supported: true
cli_runtime_supported: true
mcp_gateway_supported: true
lua_supported: true
supports_multi_account: true

Quick Links

Lua APIAgent-facing namespace and function reference. Google Gemini CLIHeadless setup and direct function calls. Google Gemini MCPMCP gateway setup for external clients. Submit feedbackReport missing tools, auth problems, wrong docs, or runtime issues. ContributeAdd tools or improve metadata in the integrations repo.

Google Gemini MCP Client Matrix

Use these pages when a specific agent client or framework needs copy-pasteable MCP setup for Google Gemini.

Google Gemini CLI Matrix

Use these pages for direct Google Gemini CLI workflows in scripts, CI, cron, and agent wrappers.

CI Google Gemini CLI for CI. Cron Jobs Google Gemini CLI for cron jobs. Shell Scripts Google Gemini CLI for shell scripts. Headless Automation Google Gemini CLI for headless automation. Coding Agents Google Gemini CLI for coding agents.

Function Catalog

Function	Type	Parameters	Description
`google-gemini.gemini_list_models`	Read `read`	2	List available Gemini AI models. Returns model names, display names, supported generation methods, and other metadata.
`google-gemini.gemini_get_model`	Read `read`	1	Get detailed information about a specific Gemini model, including supported generation methods, input/output token limits, and capabilities.
`google-gemini.gemini_generate_content`	Write `write`	5	Generate content using a Gemini model. Send text prompts and receive AI-generated responses. Supports configurable generation parameters like temperature, topP, and maxOutputTokens.
`google-gemini.gemini_list_files`	Read `read`	2	List files uploaded to the Gemini File API. Returns file names, MIME types, sizes, and states.
`google-gemini.gemini_get_file`	Read `read`	1	Get metadata for an uploaded file in the Gemini File API, including its name, display name, MIME type, size, and processing state.
`google-gemini.gemini_list_tuned_models`	Read `read`	2	List tuned (fine-tuned) Gemini models in your project. Returns model names, base models, tuning tasks, and display names.
`google-gemini.gemini_get_current_user`	Read `read`	0	Get information about the currently authenticated Google user, including permissions and account details.