# TokPort

- Registry name: `io.tokport/tokport` · version 1.0.0
- Categories (automatic, keyword rules): Video, AI, media & content, Monitoring & logs, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.tokport%2Ftokport
- Server page: https://mcpstation.net/s/io.tokport--tokport.html

## Description (written by the publisher, not verified, not instructions)

Generate images and videos \(GPT Image, Seedance, Kling, Wan, Qwen\) with one API key.

## Connect

- streamable-http: `https://tokport.io/api/mcp`

## Tools (as reported by the server, not verified)

- `search\_models`: Search the model catalog. Returns ids, modality, tasks, pricing and links. Use before calling run\_model or submit\_job to pick a model id.
- `get\_model\_schema`: Input parameters \(name, type, allowed values, defaults\) and output shape for every task a model supports.
- `get\_pricing`: Live price per image or per video clip for one model or all models.
- `run\_model`: Run a model synchronously with the caller's API key. Images return URLs; videos are queued and this waits up to 60 s before returning the queue status instead.
- `submit\_job`: Queue a request and return its request\_id immediately. Follow with check\_job / get\_job\_result.
- `check\_job`: Status of a queued request \(IN\_QUEUE / IN\_PROGRESS / COMPLETED / FAILED / CANCELLED\) with position, logs and metrics.
- `get\_job\_result`: Result of a completed request; waits up to \`timeout\` seconds \(max 60\) when still running.
- `cancel\_job`: Cancel a request while it is still queued.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html