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 Coding Agents

Use the fal.ai CLI for coding agents with headless JSON commands, schema discovery, credentials, and permission controls.

7 functions 5 read 2 write API key auth

Submit fal.ai feedback View package source

fal.ai CLI for Coding Agents

Let coding agents discover schemas and execute integration functions through CLI commands or MCP.

Use this pattern when another coding agent needs exact commands and schema discovery. The fal.ai CLI uses the same integration registry as the TUI, Lua runtime, and MCP gateway, but returns predictable command output for automation.

Command Shape

# fal.ai CLI for Coding Agents
kosmokrator integrations:configure fal --set api_key="$FAL_API_KEY" --enable --read allow --write ask --json
kosmo integrations:call fal.fal_list_models '{}' --json

Discovery Before Execution

Agents and scripts can inspect fal.ai docs and schemas 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

Useful fal.ai CLI Functions

Function	Type	Parameters	Description
`fal.fal_list_models`	Read	none	List available fal.ai models. Returns model IDs, descriptions, and capabilities.
`fal.fal_submit_request`	Write	model_id, input, webhook_url	Submit a generation request to a fal.ai model. Returns the request ID for tracking. Poll get_request_status for progress.
`fal.fal_get_request_status`	Read	model_id, request_id	Get the status of a submitted fal.ai request. Returns queue position and processing state.
`fal.fal_get_result`	Read	model_id, request_id	Get the result of a completed fal.ai request. Returns generated media URLs and metadata.
`fal.fal_list_files`	Read	none	List files stored in fal.ai storage. Returns file names, URLs, and metadata.
`fal.fal_upload_file`	Write	file_path, file_name	Upload a file to fal.ai storage for use as model input. Returns the file URL.
`fal.fal_get_current_user`	Read	none	Get current fal.ai user profile and account information.

Automation Notes

Use --json for machine-readable output.
Keep credentials out of argv by using environment variables or stored KosmoKrator configuration.
Configure read/write policy before unattended runs; use --force only for trusted automation.
Use the MCP gateway instead when the agent needs dynamic tool discovery inside a conversation.

Related fal.ai CLI Pages

CI fal.ai CLI for CI. Cron Jobs fal.ai CLI for cron jobs. Shell Scripts fal.ai CLI for shell scripts. Headless Automation fal.ai CLI for headless automation.