Topaz MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | Yes | Your RunAPI API key. Create one at runapi.ai. |
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. |
| upscale_imageB | Create a Topaz task on RunAPI (upscale image). Returns a task id, status, and output URLs. |
| upscale_videoB | Create a Topaz task on RunAPI (upscale video). Returns a task id, status, and output URLs. |
| get_taskC | Fetch the current status and latest result payload for a topaz task. |
| check_pricingB | Look up RunAPI pricing for the topaz 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 5 tools
Each tool targets a clearly distinct action: upscale_image and upscale_video split by media type, get_task polls status, check_pricing handles billing lookup, and login handles auth. No two tools could reasonably be confused for one another.
Four of five tools follow a clean verb_noun pattern (upscale_image, upscale_video, get_task, check_pricing). Only 'login' deviates as a bare verb, which is a minor but forgivable inconsistency.
Five tools is well-scoped for a focused image/video upscaling service: two task-creation tools, one status poller, one pricing lookup, and one auth tool. Nothing feels padded or missing at the count level.
The core lifecycle (auth, create upscale task, poll status, check pricing) is covered, and results come back as output URLs. However, there is no cancel/delete task, no list-tasks, and no explicit result-download tool, leaving minor gaps an agent must work around.