Grok Bot MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROK_BOT_POLL_MS | No | How often to check for a reply, in milliseconds. | 2000 |
| GROK_BOT_APP_NAME | No | The app's name, if yours differs. | Grok Bot |
| GROK_BOT_BUNDLE_ID | No | The app's bundle ID, used to switch on its accessibility tree. | com.anysphere.sand |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_agentsA | List the agents (Bots) in the Grok Bot desktop app sidebar, and which chat is open. Call this first to check that the app is reachable. |
| read_messagesA | Read recent messages from an agent chat in Grok Bot, including any multiple-choice question the agent is waiting on. Opens that chat in the app if an agent is given. |
| send_messageA | Send a message to an agent in the Grok Bot desktop app. Visibly switches to that chat, types the message and presses Enter. By default waits for the agent to finish replying and returns its reply messages (including any multiple-choice question). Ask the user first if the message would make the agent act outside the app (email, purchases, applications, account changes). |
| answer_choiceA | Click an option on a multiple-choice question an agent asked in Grok Bot (e.g. "What should we tackle next?"). Pass a letter ("A", "B"…) or the start of the option text. Waits for the reply by default. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool maps to a distinct action on a distinct aspect of the Grok Bot app: enumerating bots, reading a chat, writing to a chat, and clicking a choice option. There is no plausible confusion between read_messages and send_message, and answer_choice is clearly the only tool for responding to multiple-choice prompts.
All four names follow a clean verb_noun snake_case pattern (list_agents, read_messages, send_message, answer_choice). Verb choice is also semantically precise—list vs read vs send vs answer—reinforcing the distinction.
Four tools is a tight, well-scoped surface for driving a single desktop chat app. Each tool covers an indispensable part of the interaction loop (discover, read, write, reply to prompt) with no filler.
The core lifecycle—find the app, read a chat, send a message, answer a prompt—is fully covered with no dead ends. Minor gaps exist around starting a brand-new agent/chat or retrieving fuller conversation history, but agents can work around these via send_message and read_messages.