Omnichannel MCP Server for Grok Build

Connect your Grok Build assistant to ChatbotX via MCP SSE. Manage customer conversations, CRM contacts, tags, and chatbot flows across your connected customer channels.

Read the Docs Start for $0

Please make sure there is always a human in the loop.

Connect ChatbotX MCP to Grok Build

Paste the prompt command into your Grok Build interface to connect automatically, or configure it manually using the settings block below.

Run in Grok Build CLI

> grok build add-tool chatbotx --sse https://app.chatbotx.io/mcp/sse --token YOUR_WORKSPACE_TOKEN

or configure manually

grok.config.json

MCP config

{
  "pipeline": {
    "tools": {
      "chatbotx": {
        "type": "sse",
        "url": "https://app.chatbotx.io/mcp/sse",
        "headers": {
          "x-workspace-token": "YOUR_WORKSPACE_TOKEN"
        }
      }
    }
  }
}

Grok Build MCP Integration

Grok Build reads this page and wires up the MCP. You approve the connection.

It fetches this page, discovers the MCP endpoint, and asks you to confirm before connecting.

chatbotx.io/grok-build

# ChatbotX Model Context Protocol (MCP) Server for Grok Build

Connect xAI Grok Build developer agent to ChatbotX via MCP SSE. Automate CI/CD customer notification pipelines, inspect webhook error logs, and manage CRM state programmatically from your build workflows.

## Connection Setup for Grok Build
- Protocol: Model Context Protocol (MCP) via Server-Sent Events (SSE)
- Endpoint: https://app.chatbotx.io/mcp/sse
- Authentication: Header "x-workspace-token: <YOUR_WORKSPACE_TOKEN>"
- Documentation: https://chatbotx.io/docs/mcp/introduction

### Build Configuration
```toml
[mcp.servers.chatbotx]
endpoint = "https://app.chatbotx.io/mcp/sse"
headers = { "x-workspace-token" = "YOUR_WORKSPACE_TOKEN" }
```

## Available MCP Tools
- contacts_search: Query contact records by identifier during build and test runs.
- contacts_tag: Mark customer accounts with build status tags (e.g., "Deployed:v2.4").
- contacts_custom_field: Mutate release version or feature flag attributes on contact profiles.
- flows_trigger: Trigger automated deployment alerts or maintenance notices to customers.
- conversations_list: Inspect incoming customer alerts related to service outages.
- messages_send: Send real-time deployment status updates to Telegram or WhatsApp channels.
- broadcasts_list: Review release announcement broadcast reach.
- channels_list: Verify API endpoint health and webhook reliability.

## Developer Workflows for Grok Build
- "Following deployment of release v3.1, trigger notification flow to all contacts tagged 'Beta Tester'."
- "Inspect webhook delivery failures on Zalo OA and generate an error summary for the engineering team."
- "Verify that test contact '[email protected]' receives the automated transactional alert via SMTP."

## Supported Messaging Channels
WhatsApp, Messenger, Instagram, TikTok, Telegram, Zalo OA, Webchat, SMTP, and API.

Prompt Examples for Grok Build

Once connected, you can converse with your customer base and execute omnichannel actions in plain language.

Send Omnichannel Message

"Send a WhatsApp message to +123456789 saying their order #9821 has shipped with tracking link."

Query CRM & Contacts

"Find the contact for [email protected], check their conversation history, and tag them as 'VIP Lead'."

Trigger Visual Flows

"Trigger the Onboarding Drip Sequence for the newly registered lead on Instagram."

Audit Live Inbox

"List all unread conversations in Messenger and summarize what customers are asking today."

Autonomous Multi-Channel Execution

ChatbotX standardizes your messaging channels into clean MCP tool calls with safe guardrails.

Unified MCP Architecture

One SSE endpoint provides 380+ tools covering WhatsApp, Messenger, Zalo, Telegram, Email, and Webchat.

Enterprise Security

Workspace token authentication, granular tool whitelisting, and strict human-in-the-loop approvals for sensitive actions.

Real-time State Sync

Changes to contact fields, custom tags, or conversation status sync immediately across your ChatbotX dashboard and CRM.

Works with Every MCP Client

ChatbotX MCP works seamlessly with any AI agent runtime that supports Model Context Protocol.

DeepSeek

Open Reasoning Model

High-performance open reasoning models (V3 & R1). Connect via Cherry Studio or Cline to handle complex customer support logic.

Explore DeepSeek Integration

Kimi K3

Moonshot AI Agent

Moonshot AI agent with 2M token context. Analyze complete conversation histories and trigger multi-step chatbot flows.

Explore Kimi K3 Integration

Supported Messaging & Customer Channels

Connect your channels in ChatbotX once, then automate customer conversations to any of them via your AI assistant.

Messenger

Instagram

TikTok

Zalo OA

Webchat

SMTP

API