seedream-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | Yes | Your RunAPI API key |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| loginA | Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json. |
| decompose_layersC | Create a Seedream task on RunAPI (decompose layers). Returns a task id, status, and output URLs. |
| edit_imageB | Create a Seedream task on RunAPI (edit image). Returns a task id, status, and output URLs. |
| text_to_imageB | Create a Seedream task on RunAPI (text to image). Returns a task id, status, and output URLs. |
| get_taskA | Fetch the current status and latest result payload for a seedream task. |
| check_pricingB | Look up RunAPI pricing for the seedream model line. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
The three task-creating tools target clearly distinct image operations (decompose_layers, edit_image, text_to_image), and login/get_task/check_pricing serve separate purposes. The only mild overlap is that all three creators share near-identical description phrasing, but their intents remain distinguishable.
Most tools follow a snake_case verb_noun pattern (get_task, check_pricing, decompose_layers, edit_image, text_to_image). 'login' is the sole noun-less outlier, which is a minor deviation rather than a real inconsistency.
Six tools is well-scoped for an image-generation API surface: one auth, one status poller, one pricing lookup, and three generation modes. Nothing seems padded or missing count-wise.
The core lifecycle (authenticate, create task in three modes, poll status, check pricing) is covered, giving a usable end-to-end flow. Minor gaps exist such as cancelling or listing tasks, but agents can work around these.