Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
AUTOGROK Desk is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Pay-per-call web jobs for agents: URL probe, page extract, watch, JSON shape, researched briefs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http autogrok-desk-mcp https://desk.grokaiapps.com/mcp
# 2 — ask your agent for something these tools do
# url_probe, page_extract, watch_once and 4 more
AUTOGROK Desk costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http autogrok-desk-mcp https://desk.grokaiapps.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Call when you need a cheap reachability/health check before a heavier fetch. Probes a public http(s) URL (HEAD, GET fallback): status, final URL, content-type, timing. No full body download (GET peeks ≤8KB). SSRF-safe public hosts only. Not for authenticated or private network URLs. Price: $0.03 USDC per call (x402 on Base) or 1 prepaid pack credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL to probe |
| method | string | no | Prefer HEAD (default); GET peeks at most 8KB |
Call when an agent needs readable main content from a public web page as markdown plus title/description. Use for summarization, RAG ingest, or quoting without a browser. Fetches once; blocks private/SSRF targets. Not for authenticated, paywalled, or non-HTML resources. Price: $0.05 USDC per call (x402 on Base) or 1 prepaid pack credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) HTML page URL |
Call for a one-shot change detector: fetch a public URL, hash normalized main text (sha256), optionally compare to previous_hash. Returns hash, changed true/false/null, word_count. Use for cheap page-watch loops; not a persistent webhook subscription. Price: $0.10 USDC per call (x402 on Base) or 1 prepaid pack credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL to fingerprint |
| previous_hash | string | no | sha256 from a previous watch-once call, to detect change |
Call when you have messy text (JSON blob or key:value lines) and need a heuristic object shaped by schema_hint — no LLM. Cap 50k chars. Use to normalize tool dumps before structured follow-up. Not for NLP understanding or free-form writing. Price: $0.15 USDC per call (x402 on Base) or 1 prepaid pack credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Raw text or JSON to reshape (≤50k chars) |
| schema_hint | string | yes | Free-text hint of desired field names / shape |
Call when you need a researched written brief on a topic (not instant). Delivered within 24h, usually same day: ~500 words default (max_words 50-1500), at least 3 cited public source links. Returns job id + dueBy now; poll GET /v1/jobs/:id (free) for result {title, summary, body_markdown, sources, word_count}. Public web sources only. Price: $0.25 USDC per call (x402 on Base) or 1 prepaid pack cre
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | yes | What the brief should cover |
| max_words | integer | no | Target length (50–1500 words, default 500) |
Call when you need decision-grade research, not a quick note. Long-form brief delivered within 24h: ~1500 words (1200-2000), executive summary + key findings + analysis, at least 8 cited public sources, operator-checked. Returns job id + dueBy; poll GET /v1/jobs/:id (free) for {title, summary, body_markdown, sources, word_count}. Free sample: /samples/brief-x402-bazaar-discovery.md Price: $9.00 US
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | yes | What the deep brief should cover |
| focus | string | no | Optional angle, audience, or questions to answer |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Job id returned by brief |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AUTOGROK Desk or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish AUTOGROK Desk can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.