call-grokbot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CALL_GROKBOT_AGENTS | No | Comma-separated names, or a JSON array of names / `{name,description}` objects (defaults to all existing bots) | |
| CALL_GROKBOT_AUTH_MODE | No | `browser` or explicit `api-key` | browser |
| CALL_GROKBOT_SETTLE_MS | No | Quiet interval after confirmed completion | 1500 |
| CALL_GROKBOT_STATE_DIR | No | Local contacts and cross-process locks (defaults to the OS state directory) | |
| CALL_GROKBOT_CURSOR_CLI | No | Absolute path to the official `agent` executable (auto-detected by default) | |
| CALL_GROKBOT_API_BASE_URL | No | Official origin or a loopback test server; other hosts are refused | https://api2.cursor.sh |
| CALL_GROKBOT_DISABLED_TOOLS | No | Comma-separated tool names to omit | |
| CALL_GROKBOT_MAX_WAIT_SECONDS | No | Maximum allowed tool wait | 600 |
| CALL_GROKBOT_REQUEST_TIMEOUT_MS | No | Timeout per unary HTTP request | 20000 |
| CALL_GROKBOT_DEFAULT_WAIT_SECONDS | No | Default tool wait, capped by the maximum | 45 |
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": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| askA | Send one self-contained task to an existing Grok Bot. Never creates or renames bots. running means use check, not another ask. Messages enter the account's real conversation. |
| checkA | Read new replies and wait for the previous task. Advances this machine's cursor. Never resends messages; use after running or an unconfirmed send. |
| interruptA | Stop the contacted bot's current turn, including work started in its app. Conversation and memory remain. Cannot undo completed actions. |
| listA | List existing available bots (filtered by the optional allowlist), configured names and contacts on this machine. Sends no message. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| consult | How to delegate a self-contained task to an existing Grok Bot. |
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: list discovers bots, ask sends work, check reads results, and interrupt stops work. The descriptions explicitly clarify the ask/check boundary, so an agent can select the right tool reliably.
All four names are single lowercase imperative verbs in a consistent style: list, ask, check, interrupt. There is no mixing of camelCase, snake_case, or verb/noun patterns.
Four tools is a well-scoped set for a focused bot interaction client, with each tool covering a distinct part of the loop: discovery, sending, polling, and interruption. No tool feels redundant or missing from the core count.
The surface covers the essential lifecycle: list bots, send a task, check replies, and interrupt running work. A minor gap is the lack of explicit bot detail or historical conversation retrieval beyond new replies, but the core workflow is complete.