# AgentCompute

- Registry name: `io.github.Ockram4444/agentcompute` · version 0.8.0
- Categories (automatic, keyword rules): Audio & speech, AI, media & content
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.Ockram4444%2Fagentcompute
- Server page: https://mcpstation.net/s/io.github.Ockram4444--agentcompute.html

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

Free experimental GPU tools: text generation, images and audio transcription. Shared quotas; no SLA.

## Connect

- streamable-http: `https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp`

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

- `create\_trial\_access`: Create a private 24-hour trial token automatically. No ChatGPT account, payment or manual setup. Audio: 3 jobs per session. Chat/images: 24 total submissions per rolling 24 hours, 10 per session/reported client, one active task per session, shared queue of 3. Global access issuance caps apply. Retai
- `get\_compute\_status`: Check whether the GPU provider can accept audio transcription work. Returns availability, permitted task types, and limits. Does not start a job.
- `submit\_compute\_job`: Beta users must supply their uploaded asset\_id and kind compute\_job. No accuracy guarantee is made for uploaded files. Owner legacy calls can queue the fixed synthetic benchmark. compute\_job returns a transcript; delegated\_task additionally requires word error rate at most 10% against the known refe
- `get\_compute\_job`: Read a previously submitted job by job\_id. Returns status, transcript, runtime and reference quality when complete. For queued or running jobs, wait poll\_after\_seconds before checking again. Failed or expired jobs are not successful results.
- `get\_service\_status`: Public live availability, model catalog, free-trial limits and polling guidance. No token required. Check before submitting; an offline GPU cannot execute work.
- `submit\_chat\_job`: Queue a free text task: draft, summarize, extract, translate text, reason or assist with code. No code is executed. Provide user/assistant messages, explicit consent for nonconfidential permitted content, and a stable idempotency key. Returns immediately with a job ID. Poll get\_studio\_job. Uses the
- `submit\_image\_job`: Queue a free text-to-image task from a complete scene description. Each task is independent, not an edit of a previous image. Returns a job ID; poll get\_studio\_job then get\_studio\_image for the PNG. Configured model and size appear in service status/results. No external AI fallback.
- `get\_studio\_job`: Read your own chat/image job. Includes partial text while running, final text or image availability, GPU runtime and server timings. Wait poll\_after\_seconds between checks; stop on succeeded, failed or expired. Does not create or retry work.
- `get\_studio\_image`: Return the completed image as an MCP image content block. Requires the same token/identity that submitted the job. Images expire after 24 hours from submission; download before expiry.

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