# AgentCompute (remote · u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com)

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

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/ockram4444-agentcompute/v1-mcp.md), [page](https://verifymcp.io/servers/ockram4444-agentcompute/v1-mcp)

## Channel facts

- Endpoint: `https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.8.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1410 tokens (~141/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the AgentCompute MCP server?

AgentCompute is a hosted endpoint at https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ockram4444-agentcompute 'https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ockram4444-agentcompute": {
      "url": "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ockram4444-agentcompute": {
      "type": "http",
      "url": "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ockram4444-agentcompute]
url = "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ockram4444-agentcompute": {
      "type": "remote",
      "url": "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ockram4444-agentcompute --url 'https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ockram4444-agentcompute:
    url: "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ockram4444-agentcompute": {
      "Transport": "http",
      "Url": "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ockram4444-agentcompute -t streamable-http -u 'https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ockram4444-agentcompute": {
      "type": "http",
      "url": "https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_trial_access” rewrote its description, which is the text the model reads
- [security] Tool “submit_chat_job” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 55% → 50%
- [cosmetic] “submit_chat_job” added an optional parameter “parallel”
- [cosmetic] “submit_chat_job” added an optional parameter “routing”
- [cosmetic] “submit_chat_job” made “messages” optional

### 2026-11-01 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 71, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_trial_access” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 67% → 55%
- [functional regression] Schema quality: 117 → 130
- [functional] New tool “submit_agent_job”

### 2026-10-27 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 70, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (10)

### `submit_agent_job` (~221 tokens)

Delegate a task with approved tools

Experimental local worker agent. Version 1 reads supplied documents. Set agent_task.version=2 for decimal calculations, CSV preview/filter/numeric sort/summary/group sums, and TXT/Markdown/CSV/JSON files using approved local CPU/RAM functions. Check services.agent_tools for version 2. Up to eight tool calls, eight optional documents, 24000 input characters and three files (16000 bytes each, 24000 bytes total). Set required_artifacts to exact filenames to require delivery. Version 3 requires services.agent_web and adds public HTTPS page reading and web search, with source URLs. No JavaScript browsing, logins, VM, arbitrary code or shell. Search availability and website access can vary. File contents are returned in result.agent_result.artifacts. Quotes are matched; tool outputs and factual correctness are not independently verified. Shared trial quotas. Poll get_studio_job.

Input parameters:

- `access_token` (string)
- `agent_task` (object, required)
- `consent` (boolean, required)
- `idempotency_key` (string, required)

### `create_trial_access` (~109 tokens)

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: 72 submissions per rolling 24 hours globally, 10 per session/reported client, 3 active requests per session, shared queue of 12. Parallel parts and synthesis each count toward quotas. 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_status` (~36 tokens)

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.

### `submit_compute_job` (~188 tokens)

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.

Input parameters:

- `access_token` (string): Temporary token returned by create_trial_access. Optional when Bearer authentication is configured.
- `asset_id` (string): Owned upload ID returned by POST /v1/beta/upload. Required for public beta buyers.
- `idempotency_key` (string, required): Unique request key. Keep it unchanged on retries.
- `kind` (string, required): Transcription only, or transcription with the reference quality gate.

### `get_compute_job` (~87 tokens)

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.

Input parameters:

- `access_token` (string): Temporary trial token, unless Bearer authentication is configured.
- `job_id` (string, required): Exact job_id returned by submit_compute_job.

### `get_service_status` (~39 tokens)

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.

### `submit_chat_job` (~243 tokens)

Generate text on the GPU

Default routing fairly rotates compatible idle providers. Optional parallel:{parts:2|3,objective,documents} splits document analysis and returns one synthesized result under the same job ID. Each part and synthesis count toward quotas. Otherwise provide messages. Routing fastest requires comparable configured benchmarks; lowest_cost uses configured prices, with fair fallback when metrics are unknown. No payment. 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.

Input parameters:

- `access_token` (string): Private token from create_trial_access; optional with Bearer authentication.
- `consent` (boolean, required): Confirm permission to process this nonconfidential content.
- `idempotency_key` (string, required)
- `messages` (array): At most 12,000 characters in total. End with a user message. Include previous messages for follow-up context.
- `parallel` (object)
- `routing` (object)

### `submit_image_job` (~131 tokens)

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.

Input parameters:

- `access_token` (string): Private token from create_trial_access; optional with Bearer authentication.
- `consent` (boolean, required): Confirm permission to process this nonconfidential content.
- `idempotency_key` (string, required)
- `prompt` (string, required): Complete image description. English prompts are recommended.

### `get_studio_job` (~73 tokens)

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.

Input parameters:

- `access_token` (string)
- `job_id` (string, required)

### `get_studio_image` (~61 tokens)

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.

Input parameters:

- `access_token` (string)
- `job_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ockram4444-agentcompute/v1-mcp#diagnostics

## Score history

- 2026-11-04: 74
- 2026-11-03: 73
- 2026-11-02: 73
- 2026-11-01: 73
- 2026-10-31: 72
- 2026-10-30: 72
- 2026-10-29: 71
- 2026-10-28: 71
- 2026-10-27: 72
- 2026-10-26: 71
- 2026-10-25: 71
- 2026-10-24: 70
- 2026-10-23: 70

## Common questions

### What is the AgentCompute MCP server?

AgentCompute is an MCP server listed in the public MCP registry as io.github.Ockram4444/agentcompute. Free experimental GPU tools: text generation, images and audio transcription. Shared quotas; no SLA. This page covers its hosted endpoint (https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp).

### Is the AgentCompute MCP server safe to use?

AgentCompute scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgentCompute MCP server expose?

AgentCompute exposes 10 tools: submit_agent_job, create_trial_access, get_compute_status, submit_compute_job, get_compute_job, and 5 more. Their descriptions and schemas cost roughly 1,188 tokens of context every time the server is loaded.

### Does the AgentCompute MCP server require authentication?

No. We connected to AgentCompute without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentCompute MCP server still maintained?

AgentCompute is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp
- Website: https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/agents
- Changelog RSS feed: https://verifymcp.io/servers/ockram4444-agentcompute/v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ockram4444-agentcompute/v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ockram4444-agentcompute/v1-mcp