Topaz MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Topaz MCP ServerUpscale this image and wait for it to finish."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
What Is This?
@runapi.ai/topaz-mcp is a focused MCP server for the Topaz model line on RunAPI.
It lets an MCP-compatible assistant create Topaz tasks, poll their status, and check current pricing — all through a single RunAPI API key.
check_pricing works without a key. Task creation and status polling require RUNAPI_API_KEY.
This package is a pure client; it does not run a local generation backend.
Related MCP server: grok-imagine-mcp
Quick Start
Add it to Claude Code:
claude mcp add topaz -s user -- npx -y @runapi.ai/topaz-mcp-s user: global, available in all of your projects.-s project: team-shared, written to.mcp.jsonin the current repo so it can be committed.
For other hosts, or for manual configuration, use this JSON:
{
"mcpServers": {
"topaz": {
"command": "npx",
"args": ["-y", "@runapi.ai/topaz-mcp"],
"env": { "RUNAPI_API_KEY": "${RUNAPI_API_KEY}" }
}
}
}Create an API key at runapi.ai and expose it as RUNAPI_API_KEY.
See examples/ for ready-made config files for Claude, Cursor, Windsurf, VS Code, and Roo.
Tools
Tool | Auth | Purpose |
| Yes | Create a Topaz task (upscale image) and optionally poll until it reaches a terminal status. Returns the task id, status, output URLs, and a price snapshot. |
| Yes | Create a Topaz task (upscale video) and optionally poll until it reaches a terminal status. Returns the task id, status, output URLs, and a price snapshot. |
| Yes | Fetch the current status and latest payload for an existing task. |
| No | Look up the current price for a Topaz model and endpoint. |
Models
Topaz covers 2 models across 2 endpoints. Each tool accepts the models listed for it:
Tool | Models |
|
|
|
|
Call check_pricing for the current price of any model. Model availability can change between releases.
Examples
Ask your assistant in natural language; it uses the tools to confirm pricing and run the task.
Create a task
Run a Topaz upscale image task with RunAPI.The assistant calls check_pricing to confirm the cost, then upscale_image, and returns the task id, status, and output URLs.
Submit without waiting
Create the task but don't wait for it to finish.The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.
Check pricing
What does Topaz cost?The assistant calls check_pricing and shows the current snapshot, or links to runapi.ai/pricing.
Configuration
The server reads the API key in this order:
RUNAPI_API_KEYenvironment variable~/.config/runapi/config.json
Example config file:
{
"apiKey": "your_runapi_key"
}Do not commit real API keys. Get one at runapi.ai; pricing is listed at runapi.ai/pricing.
License
Licensed under the Apache License, Version 2.0.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/runapi-ai/topaz-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server