# Call Grok Bot

The Call Grok Bot MCP server for Claude Code and Codex sends tasks to an existing Grok Bot. It runs when an agent needs to ask a bot for work or check its reply.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 4 repo stars
- Author: ZensHQ
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ZensHQ/call-grokbot
- Updated: 2026-11-07
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/call-grok-bot

## What it does

Call Grok Bot forwards a task to an existing Grok Bot and streams back its replies. A local MCP process communicates over stdio, and an active task can be interrupted. The bot retains its own conversation, memory, and connected tools.

Setup requires Node.js 22.13+, npm, Git, the official Cursor CLI, and a Grok account with at least one bot already created. Sign in to Codex or Claude Code, then authenticate the Cursor CLI in a browser with the account that owns the bot. Use the bot’s exact name. The bot cannot see the coding session or project files automatically, so include relevant details in the task.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `CALL_GROKBOT_AUTH_MODE` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env CALL_GROKBOT_AUTH_MODE=<CALL_GROKBOT_AUTH_MODE> --transport stdio call-grok-bot -- npx -y call-grokbot
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add call-grok-bot --env CALL_GROKBOT_AUTH_MODE=<CALL_GROKBOT_AUTH_MODE> -- npx -y call-grokbot
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "call-grok-bot": {
            "command": "npx",
            "args": [
                "-y",
                "call-grokbot"
            ],
            "env": {
                "CALL_GROKBOT_AUTH_MODE": "<CALL_GROKBOT_AUTH_MODE>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "call-grok-bot": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "call-grokbot"
            ],
            "env": {
                "CALL_GROKBOT_AUTH_MODE": "<CALL_GROKBOT_AUTH_MODE>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e CALL_GROKBOT_AUTH_MODE=<CALL_GROKBOT_AUTH_MODE> call-grok-bot npx -y call-grokbot
```
Replace <…> with your own values

## When to use it
- send a task to an existing Grok Bot
- receive bot replies in a coding-agent session
- check whether a submitted task has finished
- interrupt a bot that is working on a task

## Example prompts
- List my existing bots without messaging any of them.
- Ask my existing bot “Research Bot” to reply with exactly PONG, then check that the task has finished.
- Send “Research Bot” this brief: review the supplied facts and return a concise answer.

## Similar
- [xai-grok-onboarding](https://affpapa.org/en/nevibecode/skills/xai-grok-onboarding.md) — skill · 2300 installs
- [scenario-grok-imagine-image](https://affpapa.org/en/nevibecode/skills/scenario-grok-imagine-image.md) — skill · 847 installs
- [scenario-grok-imagine-video](https://affpapa.org/en/nevibecode/skills/scenario-grok-imagine-video.md) — skill · 839 installs
- [xai-grok-imagine-video](https://affpapa.org/en/nevibecode/skills/xai-grok-imagine-video.md) — skill · 140 installs
- [xai-grok-imagine-image](https://affpapa.org/en/nevibecode/skills/xai-grok-imagine-image.md) — skill · 136 installs
- [grok-mcp](https://affpapa.org/en/nevibecode/mcp/grok-mcp.md) — MCP server · ★ 11 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
