# AUTOGROK Desk (remote · desk.grokaiapps.com)

Pay-per-call web jobs for agents: URL probe, page extract, watch, JSON shape, researched briefs.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

> **Recent critical change**: Authorization (2026-10-22). See the changelog below before you install this server.

## Components

- remote · `desk.grokaiapps.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/com-grokaiapps-desk-autogrok-desk/desk.md), [page](https://verifymcp.io/servers/com-grokaiapps-desk-autogrok-desk/desk)

## Channel facts

- Endpoint: `https://desk.grokaiapps.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (tip_remaining).
  - 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**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1609 tokens (~178/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AUTOGROK Desk MCP server?

AUTOGROK Desk is a hosted endpoint at https://desk.grokaiapps.com/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 com-grokaiapps-desk-autogrok-desk 'https://desk.grokaiapps.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-grokaiapps-desk-autogrok-desk": {
      "url": "https://desk.grokaiapps.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-grokaiapps-desk-autogrok-desk": {
      "type": "http",
      "url": "https://desk.grokaiapps.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-grokaiapps-desk-autogrok-desk]
url = "https://desk.grokaiapps.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-grokaiapps-desk-autogrok-desk": {
      "type": "remote",
      "url": "https://desk.grokaiapps.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-grokaiapps-desk-autogrok-desk --url 'https://desk.grokaiapps.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-grokaiapps-desk-autogrok-desk:
    url: "https://desk.grokaiapps.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-grokaiapps-desk-autogrok-desk": {
      "Transport": "http",
      "Url": "https://desk.grokaiapps.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-grokaiapps-desk-autogrok-desk -t streamable-http -u 'https://desk.grokaiapps.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-grokaiapps-desk-autogrok-desk": {
      "type": "http",
      "url": "https://desk.grokaiapps.com/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.

### 2026-11-05 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 69, 0)

- [security] Tool “brief” rewrote its description, which is the text the model reads
- [security] Tool “deep_brief” rewrote its description, which is the text the model reads
- [security] Tool “json_shape” rewrote its description, which is the text the model reads
- [security] Tool “page_extract” rewrote its description, which is the text the model reads
- [security] Tool “url_probe” rewrote its description, which is the text the model reads
- [security] Tool “watch_once” rewrote its description, which is the text the model reads

### 2026-10-24 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 68, +1)

- [critical regression] Authorization: unverified → fail
- [security] New tool “tip_remaining”, which the server declares destructive
- [security] Tool “brief” rewrote its description, which is the text the model reads
- [security] Tool “deep_brief” rewrote its description, which is the text the model reads
- [security] Tool “json_shape” rewrote its description, which is the text the model reads
- [security] Tool “page_extract” rewrote its description, which is the text the model reads
- [security] Tool “url_probe” rewrote its description, which is the text the model reads
- [security] Tool “watch_once” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1221 → 1487
- [functional] New tool “support_request”

## MCP tools (9)

### `url_probe` (~195 tokens)

URL probe ($0.03)

Check if a URL is up. Sends a HEAD request (GET fallback that reads at most 8 KB) to a public http(s) URL and returns the HTTP status code, ok true/false, final URL after redirects, content type, content length and response time in ms. A cheap uptime, health or broken-link check before a heavier fetch. Public hosts only; private, local and logged-in URLs are refused. Price: $0.03 USDC per call (x402 on Base) or 1 prepaid pack credit. Failed calls aren't charged when you pay per call with x402: if the job errors, the USDC payment is never settled. With pack credits (X-Entitlement-Key), a call that fails gives its credit back.

Input parameters:

- `method` (string): Prefer HEAD (default); GET peeks at most 8KB
- `url` (string, required): Public http(s) URL to probe

### `page_extract` (~185 tokens)

Page extract ($0.05)

Extract the readable text of a web page as clean markdown. Fetches one public http(s) HTML page and returns its main content as markdown, plus title, meta description, byline and a short excerpt, with menus and page clutter removed. Useful for summarizing, quoting, or feeding a page to an LLM or RAG index without a browser. Not for logged-in, paywalled or non-HTML URLs (such as PDFs); private hosts are refused. Price: $0.05 USDC per call (x402 on Base) or 1 prepaid pack credit. Failed calls aren't charged when you pay per call with x402: if the job errors, the USDC payment is never settled. With pack credits (X-Entitlement-Key), a call that fails gives its credit back.

Input parameters:

- `url` (string, required): Public http(s) HTML page URL

### `watch_once` (~193 tokens)

Watch once ($0.10)

Detect whether a web page has changed since the last check. Fetches a public URL, normalizes its main text and returns a sha256 hash, changed true/false against the previous_hash sent in (null on the first check), word count and fetch time. A one-shot change monitor for price, policy or docs pages. Each call is a single check; there are no webhooks or stored subscriptions. Price: $0.10 USDC per call (x402 on Base) or 1 prepaid pack credit. Failed calls aren't charged when you pay per call with x402: if the job errors, the USDC payment is never settled. With pack credits (X-Entitlement-Key), a call that fails gives its credit back.

Input parameters:

- `previous_hash` (string): sha256 from a previous watch-once call, to detect change
- `url` (string, required): Public http(s) URL to fingerprint

### `json_shape` (~194 tokens)

JSON shape ($0.15)

Turn messy text into structured JSON. Parses a JSON blob or key: value lines (up to 50,000 characters) into an object using the field names given in schema_hint, and returns notes on what matched. Rule-based parsing with no LLM, so results are fast and predictable. Useful for normalizing tool output, logs or form dumps before further processing. Not for free-form language understanding or writing. Price: $0.15 USDC per call (x402 on Base) or 1 prepaid pack credit. Failed calls aren't charged when you pay per call with x402: if the job errors, the USDC payment is never settled. With pack credits (X-Entitlement-Key), a call that fails gives its credit back.

Input parameters:

- `schema_hint` (string, required): Free-text hint of desired field names / shape
- `text` (string, required): Raw text or JSON to reshape (≤50k chars)

### `brief` (~200 tokens)

Brief ($0.25)

Research brief with cited sources on any topic, written to order (not instant). Returns a job id and due time right away; the finished brief (title, summary, markdown body, source links, word count) is ready within 24 hours, usually the same day, at GET /v1/jobs/:id, which is free. About 500 words by default (50-1500 via max_words), with at least 3 cited public web sources. Price: $0.25 USDC per call (x402 on Base) or 1 prepaid pack credit. Failed calls aren't charged when you pay per call with x402: if the job errors, the USDC payment is never settled. With pack credits (X-Entitlement-Key), a call that fails gives its credit back.

Input parameters:

- `max_words` (integer): Target length (50–1500 words, default 500)
- `topic` (string, required): What the brief should cover

### `deep_brief` (~210 tokens)

Deep brief ($9.00)

In-depth research report with cited sources, for decisions that need more than a quick note. About 1,500 words (1,200-2,000) with an executive summary, key findings and analysis, at least 8 cited public sources, and an operator check before delivery. Returns a job id and due time right away; the report is ready within 24 hours at GET /v1/jobs/:id, which is free. Free sample: /samples/brief-x402-bazaar-discovery.md Price: $9.00 USDC per call (x402 on Base) or 1 prepaid pack credit. Failed calls aren't charged when you pay per call with x402: if the job errors, the USDC payment is never settled. With pack credits (X-Entitlement-Key), a call that fails gives its credit back.

Input parameters:

- `focus` (string): Optional angle, audience, or questions to answer
- `topic` (string, required): What the deep brief should cover

### `brief_status` (~89 tokens)

Brief status (free)

Free. Check a brief ordered with the brief or deep_brief tool. Delivered within 24h (usually same day): ~500 words by default (50–1500), at least 3 cited source links. Returns status, dueBy, and result {title, summary, body_markdown, sources, word_count} when done.

Input parameters:

- `id` (string, required): Job id returned by brief

### `tip_remaining` (~139 tokens)

Tip what's left (free to call)

When you're done with a pack, tip everything left on it (unused credits at the price paid + pack balance) to AUTOGROK Desk. No new charge; it clears the pack to zero and can't be undone. Needs header X-Entitlement-Key. Call with confirm=false (or omit) to see the amount; then confirm=true with expect_usd set to that amount.

Input parameters:

- `confirm` (boolean): Must be true to tip. Omit or false to preview the amount only.
- `expect_usd` (string): The total you previewed, e.g. "0.45". The tip is refused if the total changed.

### `support_request` (~145 tokens)

Ask a person for help (free)

Open a support ticket with the people behind AUTOGROK Desk (payment or receipt, a failed job, credits, anything else). Send X-Entitlement-Key on the connection or include an email. Returns a ticket id like HELP-XXXX. No automatic reply is sent; a person answers, usually within 1 business day.

Input parameters:

- `email` (string): Where to reply. Defaults to the pack's checkout email.
- `message` (string, required): What happened, in a few sentences. Include a job id if you have one.
- `topic` (string, required): payment = payment or receipt; job = a job failed or looks wrong; credits = credits or balance; other

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-grokaiapps-desk-autogrok-desk/desk#diagnostics

## Score history

- 2026-11-05: 74
- 2026-11-04: 73
- 2026-11-03: 73
- 2026-11-02: 73
- 2026-11-01: 72
- 2026-10-31: 72
- 2026-10-30: 71
- 2026-10-29: 71
- 2026-10-28: 70
- 2026-10-27: 70
- 2026-10-26: 69
- 2026-10-25: 69
- 2026-10-24: 69
- 2026-10-23: 68
- 2026-10-22: 68
- 2026-10-21: 67
- 2026-10-20: 67
- 2026-10-19: 67
- 2026-10-18: 67
- 2026-10-17: 66
- 2026-10-16: 66
- 2026-10-15: 65
- 2026-10-14: 65
- 2026-10-13: 64

## Common questions

### What is the AUTOGROK Desk MCP server?

AUTOGROK Desk is an MCP server listed in the public MCP registry as com.grokaiapps.desk/autogrok-desk. Pay-per-call web jobs for agents: URL probe, page extract, watch, JSON shape, researched briefs. This page covers its hosted endpoint (https://desk.grokaiapps.com/mcp).

### Is the AUTOGROK Desk MCP server safe to use?

AUTOGROK Desk 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 AUTOGROK Desk MCP server expose?

AUTOGROK Desk exposes 9 tools: url_probe, page_extract, watch_once, json_shape, brief, and 4 more. Their descriptions and schemas cost roughly 1,550 tokens of context every time the server is loaded.

### Does the AUTOGROK Desk MCP server require authentication?

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

### Is the AUTOGROK Desk MCP server still maintained?

AUTOGROK Desk is still listed as active in the MCP registry. We last reached this channel on 5 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://desk.grokaiapps.com/mcp
- Website: https://desk.grokaiapps.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-grokaiapps-desk-autogrok-desk/desk.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-grokaiapps-desk-autogrok-desk/desk.json
- HTML version of this page: https://verifymcp.io/servers/com-grokaiapps-desk-autogrok-desk/desk