AI Media Router
by jutsuhq
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FFMPEG | No | Path to the ffmpeg binary, used when it is not on PATH. Enables previews, media probing and media operations. | |
| FAL_KEY | No | API key for the fal.ai provider (example of a provider key). Provider keys are set with `ai-media-router keys set <NAME>` or via the process environment / config.toml `[env]`. | |
| FFPROBE | No | Path to the ffprobe binary, used when it is not on PATH. | |
| COMFYUI_URL | No | URL of your own ComfyUI server (e.g. http://127.0.0.1:8188) to enable provider `comfyui`; jobs cost 0 USD. | |
| KIE_API_KEY | No | API key for the kie.ai provider (example of a provider key). Provider keys are set with `ai-media-router keys set <NAME>` or via the process environment / config.toml `[env]`. | |
| COMFYUI_TOKEN | No | Optional token for authenticating with your ComfyUI server. | |
| EMBEDDINGS_URL | No | Base URL of any OpenAI-compatible embeddings endpoint (such as Ollama) to enable `similar_assets`; used together with EMBEDDINGS_MODEL. | |
| EMBED_METADATA | No | Set to "false" to store provider files unchanged and skip embedding provenance metadata into PNG, JPEG and video files. | true |
| EMBEDDINGS_MODEL | No | Embeddings model name for the endpoint given in EMBEDDINGS_URL. | |
| EMBEDDINGS_API_KEY | No | OpenAI API key used to enable `similar_assets` via OpenAI embeddings. | |
| AI_MEDIA_ROUTER_HOME | No | Sets the home directory for the library, database, config and assets. Defaults to the OS data dir (e.g. ~/Library/Application Support/jutsu.ai-media-router on macOS, %APPDATA%\jutsu\ai-media-router\data on Windows, ~/.local/share/ai-media-router on Linux). | |
| AI_MEDIA_ROUTER_TOKEN | No | Bearer token required by the HTTP server when `serve` binds a non-loopback address; every request then needs `Authorization: Bearer <token>`. Also needed to enable `save_spec` / `reset_spec` unless `--allow-spec-writes` is given. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues