AgentCompute

io.github.Ockram4444Published by GitHub account Ockram4444v0.8.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableMedia & DesignAI & ML

Overview

AI-generated overview

A remote MCP server that lets an assistant queue free experimental GPU jobs for text generation, image generation and audio transcription, then poll for results

What you can do
AgentCompute exposes tools to create a private 24-hour trial token, check GPU and service availability, and submit jobs. Chat jobs draft, summarize, extract, translate or reason over text; image jobs generate a PNG from a scene description; compute jobs return transcripts for uploaded audio assets. Separate tools read job status, partial text, final text or the finished image, and report polling guidance.
When to use it
Useful for trying GPU-backed text, image or transcription work without setting up your own infrastructure, especially for one-off drafts, summaries, translations or simple images. It is experimental with shared quotas and no SLA, so it suits trials and prototypes rather than production or time-critical work.
Requirements
A remote streamable HTTP endpoint; no local runtime, account, payment or API key is declared. A trial token is created through the create_trial_access tool, and the same token or identity must be used to read jobs and images. Network access to the endpoint is required.
Before you install
Jobs are queued on a shared service with quotas, one active task per session and global issuance caps, and no accuracy guarantee is made for uploaded files. Chat submissions require explicit consent for nonconfidential permitted content, so do not send confidential material. Images expire 24 hours after submission and must be downloaded before then. No code is executed by chat jobs.

Installation

In SourceWeft

  1. Open AgentCompute in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Ockram4444%2Fagentcompute/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentcompute": {
      "type": "http",
      "url": "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
    }
  }
}

Tools

9

create_trial_access

Start a trial without login

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. Retain the token for upload and result retrieval. Reuse the session; never create new sessions to bypass quotas.

Takes no parameters.

get_compute_status

Check GPU availability

Check whether the GPU provider can accept audio transcription work. Returns availability, permitted task types, and limits. Does not start a job.

Takes no parameters.

submit_compute_job

Submit an audio transcription 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 reference. Returns a job_id to poll with get_compute_job. No payment is charged. Reuse the same idempotency_key for retries, and use a new key only for a new job.

Parameterskindrequiredasset_idaccess_tokenidempotency_keyrequired

get_compute_job

Read a GPU job result

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.

Parametersjob_idrequiredaccess_token

get_service_status

Check chat, image and audio availability

Public live availability, model catalog, free-trial limits and polling guidance. No token required. Check before submitting; an offline GPU cannot execute work.

Takes no parameters.

submit_chat_job

Generate text on the GPU

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 configured local model, no external AI fallback.

Parametersconsentrequiredmessagesrequiredaccess_tokenidempotency_keyrequired

submit_image_job

Generate an image on the GPU

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.

Parameterspromptrequiredconsentrequiredaccess_tokenidempotency_keyrequired

get_studio_job

Read text or image task status

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.

Parametersjob_idrequiredaccess_token

get_studio_image

Retrieve your generated PNG

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.

Parametersjob_idrequiredaccess_token

Version history

1
  1. v0.8.0LatestOct 23, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.