# AgentCompute English Transcription

> English WAV transcription on a GPU. No login: agents obtain temporary trial access automatically.

- name: site.chatgpt.beigemelon258.agentcompute-pilot-portal/english-transcription
- version: 0.7.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 92/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/site.chatgpt.beigemelon258.agentcompute-pilot-portal%2Fenglish-transcription
- tools: https://api.protogrid.dev/v1/servers/site.chatgpt.beigemelon258.agentcompute-pilot-portal%2Fenglish-transcription/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "english-transcription": {
      "type": "http",
      "url": "https://agentcompute-pilot-portal.beigemelon258.chatgpt.site/v1/mcp",
      "headers": {
        "Authorization": "Bearer ${ENGLISH_TRANSCRIPTION_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${ENGLISH_TRANSCRIPTION_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-24d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 92/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 9 of 9 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,589 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 83 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name
- pass `stability.new_links`: no tool change named a new site

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 9, about 1,589 tokens to load them all
- tool set hash: c90dc3d8e79ed0aaa612d38be5595237
- tools last changed: 2026-10-23T08:13:15.619Z
- badge: [![protogrid quality](https://protogrid.dev/badge/site.chatgpt.beigemelon258.agentcompute-pilot-portal/english-transcription.svg)](https://protogrid.dev/servers/site.chatgpt.beigemelon258.agentcompute-pilot-portal/english-transcription)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-23 `get_studio_image` added
  - 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.
- 2026-10-23 `get_studio_job` added
  - 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.
- 2026-10-23 `submit_image_job` added
  - 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.
- 2026-10-23 `submit_chat_job` added
  - 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.
- 2026-10-23 `get_service_status` added
  - Public live availability, model catalog, free-trial limits and polling guidance. No token required. Check before submitting; an offline GPU cannot execute work.
- 2026-10-23 `create_trial_access` changed (description)
  - before: Create a private 24-hour trial token automatically. No ChatGPT account, payment or manual setup. Limited to 3 jobs per session and shared global caps. Retain the token for upload and result retrieval. Reuse the session; never create new sessions to bypass quotas.
  - after: Create a private 24-hour trial token automatically. No ChatGPT account, payment or manual setup. Audio: 3 jobs per session. Chat/images: shared queue of 3 active tasks, no per-session job quota. Global access issuance caps apply. Retain the token for upload and result retrieval. Reuse the session; never create new sessions to bypass quotas.

Full history: https://api.protogrid.dev/v1/servers/site.chatgpt.beigemelon258.agentcompute-pilot-portal%2Fenglish-transcription/changes

## Remotes

- https://agentcompute-pilot-portal.beigemelon258.chatgpt.site/v1/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (9)

- `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: shared queue of 3 active tasks, no per-session job quota. Global access issuance caps apply. Retain the token for upload and result retrieval. Reuse the session; never create new sessions to bypass quotas.
- `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_compute_status`: Check whether the GPU provider can accept English transcription work. Returns availability, permitted task types, and limits. Does not start a job.
- `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.
- `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.
- `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.
- `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 configured local model, no external AI fallback.
- `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 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.
- `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.