MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
grokbot.tools 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.
96/100
tool-list score
6
tools declared
remote
at its publisher
—
calls last 7d
What it does
Search Grok Bot connectors, install methods, test status, and the connector wishlist.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http grokbot-tools-mcp https://mcp.grokbot.tools/mcp
# 2 — ask your agent for something these tools do
# search_connectors, get_connector, list_connectors and 3 more
grokbot.tools costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GRAll 1 server
grokbot1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
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.
Claude Codedeclared by this listing
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 grokbot-tools-mcp https://mcp.grokbot.tools/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
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.
What you approve
6 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.
Search the grokbot.tools directory of MCP connectors and plugins for Grok Bot by name, service or category, with optional filters (Grok Bot test status, install method, auth type). Returns compact summaries with the install method, auth type, honest test-status label and the grokbot.tools page URL; use get_connector for install steps and the MCP URL. Only published directory entries are returned.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free text matched against connector name, service, category and slug, e.g. 'notion' or 'payments'. |
| category | string | no | Exact category name, case-insensitive, e.g. 'Developer tools & data', 'Money', 'Design', 'Docs & search', 'Projects & docs', 'Sales & support', 'Files', 'Security'. Use list_connectors with no filters |
| status | string | no | Grok Bot test status. 'verified' = dated test inside Grok Bot. 'seen_working' = seen working, dated re-test pending. 'unknown' = not re-tested inside Grok Bot yet (includes seen_working). 'broken' = f |
| install_method | string | no | How the app gets into Grok Bot: built-in plugin (Connect apps), custom MCP URL added via chat, browser only, or unverified. |
| auth_type | string | no | 'oauth' = you sign in with your own account; 'public' = no sign-in. |
| limit | integer | no | Max results, 1-25 (default 10). Larger values are clamped to 25. |
Get the full public record for one published connector by its slug (the last part of https://grokbot.tools/connectors/{slug}): summary, install method with step-by-step instructions and sources, MCP URL (null for built-in plugins), auth type, docs link, Grok Bot test status with the last test date, notes, related wishlist requests, and the page URL. Status is never 'Verified' unless it was verifie
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Connector slug, e.g. 'notion', 'linear', 'context7'. Find slugs with search_connectors. |
Page through every published connector in the grokbot.tools directory, alphabetically, with the same optional filters as search_connectors. Returns compact summaries plus the total, the categories in use (first page), and a next_cursor to pass back for the next page. Use this when you want the whole directory; use search_connectors when you know what you are looking for. Read-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Optional free-text filter on name, service, category and slug. |
| category | string | no | Exact category name, case-insensitive, e.g. 'Developer tools & data', 'Money', 'Design', 'Docs & search', 'Projects & docs', 'Sales & support', 'Files', 'Security'. Use list_connectors with no filters |
| status | string | no | Grok Bot test status. 'verified' = dated test inside Grok Bot. 'seen_working' = seen working, dated re-test pending. 'unknown' = not re-tested inside Grok Bot yet (includes seen_working). 'broken' = f |
| install_method | string | no | How the app gets into Grok Bot: built-in plugin (Connect apps), custom MCP URL added via chat, browser only, or unverified. |
| auth_type | string | no | 'oauth' = you sign in with your own account; 'public' = no sign-in. |
| limit | integer | no | Page size, 1-50 (default 20). Larger values are clamped to 50. |
| cursor | string | no | Opaque cursor from a previous result's next_cursor. Omit for the first page. |
List the grokbot.tools wishlist: apps people want connected to Grok Bot, sorted by on-site votes or by newest. Each item has its status (requested, claimed, live), on-site vote count, the labeled seed signal ('X buzz (seed)', mentions elsewhere that are never counted as votes), a linked connector if one exists, and its page URL. Votes are only votes made on grokbot.tools and start at 0. Read-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort | string | no | 'votes' = most on-site votes first, then seed buzz (default). 'recent' = newest first. |
| status | string | no | Only requests in this state. 'live' means a connector exists. Omit for all. |
| limit | integer | no | Max results, 1-25 (default 10). Larger values are clamped to 25. |
Get one wishlist request by slug (the last part of https://grokbot.tools/requests/{slug}): status, on-site votes, the labeled seed signal, description, public sources (links to the posts it came from), the linked connector if one exists, the builder if it has been claimed, and a matching setup guide when there is one. Slugs of requests that were merged resolve to the surviving request. Read-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Request slug, e.g. 'whatsapp'. Find slugs with list_requests. |
Explains how an app gets into Grok Bot: built-in plugins (Connect apps in the sidebar), custom MCP servers (you ask the Bot in chat to add a URL; must be public HTTPS using streamable HTTP or SSE), and the browser-only route when neither exists. Includes this server's own URL as a worked example. Takes no input and reads nothing from the database.
No parameter schema on file.
Free
$0 forever
- 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 grokbot.tools or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.0.0 · scanned 23 Oct 2026
Graded from the tools this server lists, not from its source code.
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.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest40b6869a229b05a3d64d61663834f6cdcb84abd44bbd5b5c937912ed3a2f6ee9
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_connectors | no tags | |
| get_connector | no tags | |
| list_connectors | no tags | |
| list_requests | no tags | |
| get_request | no tags | |
| how_to_add_connector | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest40b6869a229b05a3
Scanned2026-10-23
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
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.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish grokbot.tools can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.