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 CLI for AI Agents

Use the Google Gemini CLI from KosmoKrator to call Google Gemini tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

7 functions 6 read 1 write API key auth

Submit Google Gemini feedback View package source

Google Gemini CLI Setup

Google Gemini can be configured headlessly with `kosmokrator integrations:configure google-gemini`.

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure google-gemini --set api_key="$GOOGLE_GEMINI_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor google-gemini --json
kosmokrator integrations:status --json

Credentials

Authentication type: API key api_key. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

Key	Env var	Type	Required	Label
`api_key`	`GOOGLE_GEMINI_API_KEY`	Secret `secret`	yes	API Key
`url`	`GOOGLE_GEMINI_URL`	URL `url`	no	API Base URL

Call Google Gemini Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call google-gemini.gemini_list_models '{
  "pageSize": 1,
  "pageToken": "example_pageToken"
}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:google-gemini gemini_list_models '{
  "pageSize": 1,
  "pageToken": "example_pageToken"
}' --json

Agent Discovery Commands

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

kosmo integrations:docs google-gemini --json
kosmo integrations:docs google-gemini.gemini_list_models --json
kosmo integrations:schema google-gemini.gemini_list_models --json
kosmo integrations:search "Google Gemini" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Google Gemini.

`google-gemini.gemini_list_models`

Read read

List available Gemini AI models. Returns model names, display names, supported generation methods, and other metadata.

Parameters: pageSize, pageToken

Generic CLI call

kosmo integrations:call google-gemini.gemini_list_models '{"pageSize":1,"pageToken":"example_pageToken"}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_list_models '{"pageSize":1,"pageToken":"example_pageToken"}' --json

`google-gemini.gemini_get_model`

Read read

Get detailed information about a specific Gemini model, including supported generation methods, input/output token limits, and capabilities.

Parameters: id

Generic CLI call

kosmo integrations:call google-gemini.gemini_get_model '{"id":"example_id"}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_get_model '{"id":"example_id"}' --json

`google-gemini.gemini_generate_content`

Write write

Generate content using a Gemini model. Send text prompts and receive AI-generated responses. Supports configurable generation parameters like temperature, topP, and maxOutputTokens.

Parameters: id, contents, temperature, topP, maxOutputTokens

Generic CLI call

kosmo integrations:call google-gemini.gemini_generate_content '{"id":"example_id","contents":"example_contents","temperature":1,"topP":1,"maxOutputTokens":1}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_generate_content '{"id":"example_id","contents":"example_contents","temperature":1,"topP":1,"maxOutputTokens":1}' --json

`google-gemini.gemini_list_files`

Read read

List files uploaded to the Gemini File API. Returns file names, MIME types, sizes, and states.

Parameters: pageSize, pageToken

Generic CLI call

kosmo integrations:call google-gemini.gemini_list_files '{"pageSize":1,"pageToken":"example_pageToken"}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_list_files '{"pageSize":1,"pageToken":"example_pageToken"}' --json

`google-gemini.gemini_get_file`

Read read

Get metadata for an uploaded file in the Gemini File API, including its name, display name, MIME type, size, and processing state.

Parameters: id

Generic CLI call

kosmo integrations:call google-gemini.gemini_get_file '{"id":"example_id"}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_get_file '{"id":"example_id"}' --json

`google-gemini.gemini_list_tuned_models`

Read read

List tuned (fine-tuned) Gemini models in your project. Returns model names, base models, tuning tasks, and display names.

Parameters: pageSize, pageToken

Generic CLI call

kosmo integrations:call google-gemini.gemini_list_tuned_models '{"pageSize":1,"pageToken":"example_pageToken"}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_list_tuned_models '{"pageSize":1,"pageToken":"example_pageToken"}' --json

`google-gemini.gemini_get_current_user`

Read read

Get information about the currently authenticated Google user, including permissions and account details.

Parameters: none

Generic CLI call

kosmo integrations:call google-gemini.gemini_get_current_user '{}' --json

Provider shortcut

kosmo integrations:google-gemini gemini_get_current_user '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

`google-gemini.gemini_list_models`

List available Gemini AI models. Returns model names, display names, supported generation methods, and other metadata.

Operation: Read read
Schema command: kosmo integrations:schema google-gemini.gemini_list_models --json

Parameter	Type	Required	Description
`pageSize`	integer	no	Maximum number of models to return per page (default: 50, max: 100).
`pageToken`	string	no	Token from a previous response to fetch the next page of results.

`google-gemini.gemini_get_model`

Get detailed information about a specific Gemini model, including supported generation methods, input/output token limits, and capabilities.

Operation: Read read
Schema command: kosmo integrations:schema google-gemini.gemini_get_model --json

Parameter	Type	Required	Description
`id`	string	yes	The model resource name (e.g., "models/gemini-2.0-flash" or "models/gemini-pro").

`google-gemini.gemini_generate_content`

Generate content using a Gemini model. Send text prompts and receive AI-generated responses. Supports configurable generation parameters like temperature, topP, and maxOutputTokens.

Operation: Write write
Schema command: kosmo integrations:schema google-gemini.gemini_generate_content --json

Parameter	Type	Required	Description
`id`	string	yes	The model resource name (e.g., "models/gemini-2.0-flash" or "models/gemini-pro").
`contents`	array	yes	Array of content parts. Each entry should have a "role" ("user" or "model") and "parts" array with objects like {"text": "Your prompt here"}.
`temperature`	number	no	Controls randomness in generation (0.0–2.0). Lower values are more deterministic, higher values more creative.
`topP`	number	no	Nucleus sampling parameter (0.0–1.0). Limits cumulative probability of tokens considered.
`maxOutputTokens`	integer	no	Maximum number of tokens to generate in the response.

`google-gemini.gemini_list_files`

List files uploaded to the Gemini File API. Returns file names, MIME types, sizes, and states.

Operation: Read read
Schema command: kosmo integrations:schema google-gemini.gemini_list_files --json

Parameter	Type	Required	Description
`pageSize`	integer	no	Maximum number of files to return per page (default: 50, max: 100).
`pageToken`	string	no	Token from a previous response to fetch the next page of results.

`google-gemini.gemini_get_file`

Get metadata for an uploaded file in the Gemini File API, including its name, display name, MIME type, size, and processing state.

Operation: Read read
Schema command: kosmo integrations:schema google-gemini.gemini_get_file --json

Parameter	Type	Required	Description
`id`	string	yes	The file resource name (e.g., "files/abc123").

`google-gemini.gemini_list_tuned_models`

List tuned (fine-tuned) Gemini models in your project. Returns model names, base models, tuning tasks, and display names.

Operation: Read read
Schema command: kosmo integrations:schema google-gemini.gemini_list_tuned_models --json

Parameter	Type	Required	Description
`pageSize`	integer	no	Maximum number of tuned models to return per page (default: 50, max: 100).
`pageToken`	string	no	Token from a previous response to fetch the next page of results.

`google-gemini.gemini_get_current_user`

Get information about the currently authenticated Google user, including permissions and account details.

Operation: Read read
Schema command: kosmo integrations:schema google-gemini.gemini_get_current_user --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.