Can I use fal.ai as a CLI?

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

Can I expose fal.ai through MCP?

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

Where are fal.ai credentials stored?

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

Can I deny write access for fal.ai MCP tools?

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

fal.ai CLI for AI Agents

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

7 functions 5 read 2 write API key auth

Submit fal.ai feedback View package source

fal.ai CLI Setup

fal.ai can be configured headlessly with `kosmokrator integrations:configure fal`.

# 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 fal --set api_key="$FAL_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor fal --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`	`FAL_API_KEY`	Secret `secret`	yes	API Key
`url`	`FAL_URL`	URL `url`	no	API Base URL

Call fal.ai Headlessly

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

kosmo integrations:call fal.fal_list_models '{}' --json

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

kosmo integrations:fal fal_list_models '{}' --json

Agent Discovery Commands

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

kosmo integrations:docs fal --json
kosmo integrations:docs fal.fal_list_models --json
kosmo integrations:schema fal.fal_list_models --json
kosmo integrations:search "fal.ai" --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 fal.ai.

`fal.fal_list_models`

Read read

List available fal.ai models. Returns model IDs, descriptions, and capabilities.

Parameters: none

Generic CLI call

kosmo integrations:call fal.fal_list_models '{}' --json

Provider shortcut

kosmo integrations:fal fal_list_models '{}' --json

`fal.fal_submit_request`

Write write

Submit a generation request to a fal.ai model. Returns the request ID for tracking. Poll get_request_status for progress.

Parameters: model_id, input, webhook_url

Generic CLI call

kosmo integrations:call fal.fal_submit_request '{"model_id":"example_model_id","input":"example_input","webhook_url":"example_webhook_url"}' --json

Provider shortcut

kosmo integrations:fal fal_submit_request '{"model_id":"example_model_id","input":"example_input","webhook_url":"example_webhook_url"}' --json

`fal.fal_get_request_status`

Read read

Get the status of a submitted fal.ai request. Returns queue position and processing state.

Parameters: model_id, request_id

Generic CLI call

kosmo integrations:call fal.fal_get_request_status '{"model_id":"example_model_id","request_id":"example_request_id"}' --json

Provider shortcut

kosmo integrations:fal fal_get_request_status '{"model_id":"example_model_id","request_id":"example_request_id"}' --json

`fal.fal_get_result`

Read read

Get the result of a completed fal.ai request. Returns generated media URLs and metadata.

Parameters: model_id, request_id

Generic CLI call

kosmo integrations:call fal.fal_get_result '{"model_id":"example_model_id","request_id":"example_request_id"}' --json

Provider shortcut

kosmo integrations:fal fal_get_result '{"model_id":"example_model_id","request_id":"example_request_id"}' --json

`fal.fal_list_files`

Read read

List files stored in fal.ai storage. Returns file names, URLs, and metadata.

Parameters: none

Generic CLI call

kosmo integrations:call fal.fal_list_files '{}' --json

Provider shortcut

kosmo integrations:fal fal_list_files '{}' --json

`fal.fal_upload_file`

Write write

Upload a file to fal.ai storage for use as model input. Returns the file URL.

Parameters: file_path, file_name

Generic CLI call

kosmo integrations:call fal.fal_upload_file '{"file_path":"example_file_path","file_name":"example_file_name"}' --json

Provider shortcut

kosmo integrations:fal fal_upload_file '{"file_path":"example_file_path","file_name":"example_file_name"}' --json

`fal.fal_get_current_user`

Read read

Get current fal.ai user profile and account information.

Parameters: none

Generic CLI call

kosmo integrations:call fal.fal_get_current_user '{}' --json

Provider shortcut

kosmo integrations:fal fal_get_current_user '{}' --json

Function Schemas

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

`fal.fal_list_models`

List available fal.ai models. Returns model IDs, descriptions, and capabilities.

Operation: Read read
Schema command: kosmo integrations:schema fal.fal_list_models --json

Parameter	Type	Required	Description
No parameters.

`fal.fal_submit_request`

Submit a generation request to a fal.ai model. Returns the request ID for tracking. Poll get_request_status for progress.

Operation: Write write
Schema command: kosmo integrations:schema fal.fal_submit_request --json

Parameter	Type	Required	Description
`model_id`	string	yes	The model identifier (e.g., "fal-ai/flux/schnell").
`input`	object	yes	An object of model input values (e.g., prompt, image_url, etc.).
`webhook_url`	string	no	A URL to receive POST notifications when the request completes.

`fal.fal_get_request_status`

Get the status of a submitted fal.ai request. Returns queue position and processing state.

Operation: Read read
Schema command: kosmo integrations:schema fal.fal_get_request_status --json

Parameter	Type	Required	Description
`model_id`	string	yes	The model identifier used when submitting the request.
`request_id`	string	yes	The request ID returned by submit_request.

`fal.fal_get_result`

Get the result of a completed fal.ai request. Returns generated media URLs and metadata.

Operation: Read read
Schema command: kosmo integrations:schema fal.fal_get_result --json

Parameter	Type	Required	Description
`model_id`	string	yes	The model identifier used when submitting the request.
`request_id`	string	yes	The request ID returned by submit_request.

`fal.fal_list_files`

List files stored in fal.ai storage. Returns file names, URLs, and metadata.

Operation: Read read
Schema command: kosmo integrations:schema fal.fal_list_files --json

Parameter	Type	Required	Description
No parameters.

`fal.fal_upload_file`

Upload a file to fal.ai storage for use as model input. Returns the file URL.

Operation: Write write
Schema command: kosmo integrations:schema fal.fal_upload_file --json

Parameter	Type	Required	Description
`file_path`	string	yes	The local file path to upload.
`file_name`	string	no	Custom file name for the upload. Defaults to the original file name.

`fal.fal_get_current_user`

Get current fal.ai user profile and account information.

Operation: Read read
Schema command: kosmo integrations:schema fal.fal_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.