Omnichannel MCP Server for Gemini
Connect your Gemini assistant to ChatbotX via MCP SSE. Manage customer conversations, CRM contacts, tags, and chatbot flows across your connected customer channels.
Please make sure there is always a human in the loop.
Connect ChatbotX MCP to Gemini
Paste the prompt command into your Gemini interface to connect automatically, or configure it manually using the settings block below.
Choose Connection Method
Select how you want to integrate Gemini with ChatbotX
Connect directly using the official Google Gemini CLI command:
Run the command below in your terminal to register ChatbotX MCP server into Gemini CLI:
gemini mcp add chatbotx https://app.chatbotx.io/mcp/messages --header "x-workspace-token: YOUR_WORKSPACE_TOKEN"
Verify your connection anytime with: gemini mcp list
Integrate into Google AI Studio using Function Calling and Custom Tools:
- Open Google AI Studio (aistudio.google.com) > Create a new Prompt.
- In the right-hand settings panel, enable Tools > Function Calling.
- Paste the OpenAPI Schema URL and provide your workspace authentication header:
Gemini 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 Model Context Protocol (MCP) Server for Google Gemini Connect Google Gemini models to ChatbotX via MCP SSE and Function Calling. Leverage Gemini 1.5/2.0 multimodal reasoning and 1M+ token context to ingest high-volume customer conversation logs, analyze sentiment, and execute omnichannel CRM actions. ## Connection Setup for Google Gemini - Protocol: Model Context Protocol (MCP) via Server-Sent Events (SSE) / Function Calling - Endpoint: https://app.chatbotx.io/mcp/messages (Streamable HTTP) - OpenAPI Schema: https://app.chatbotx.io/api/v1/openapi.json - Authentication: Header "x-workspace-token: <YOUR_WORKSPACE_TOKEN>" - Documentation: https://chatbotx.io/docs/mcp/introduction ### Gemini CLI Registration ```bash gemini mcp add chatbotx https://app.chatbotx.io/mcp/messages --header "x-workspace-token: YOUR_WORKSPACE_TOKEN" ``` ## Available MCP Tools - contacts_search: Query customer database by email, phone (+84...), or workspace ID. - contacts_tag: Apply dynamic segmentation tags based on deep reasoning analysis. - contacts_custom_field: Update custom fields (e.g., customer_sentiment, lifetime_value). - flows_trigger: Programmatically trigger visual chatbot drip sequences. - conversations_list: Ingest hundreds of conversation threads across WhatsApp, Zalo, and Messenger. - messages_send: Send personalized multi-channel responses in 40+ languages. - broadcasts_list: Analyze past campaign metrics and audience segment performance. - channels_list: Check connectivity of all connected messaging providers. ## Long-Context Workflows with Gemini - "Ingest the last 200 conversations across WhatsApp and Instagram. Identify the top 5 product feature requests and tag relevant customers." - "Analyze customer inquiry from phone:+84912345678, translate technical questions into Vietnamese, and send a WhatsApp reply." - "Audit unassigned conversations in Messenger, flag urgent billing questions, and trigger the priority support sequence." ## Supported Messaging Channels WhatsApp, Messenger, Instagram, TikTok, Telegram, Zalo OA, Webchat, SMTP, and API.
Prompt Examples for Gemini
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.
OpenClaw
Personal Autonomous AgentAutonomous personal AI agent. Manages multi-channel customer communications, tags contacts, and triggers automated flows.
Hermes Agent
Nous Research AgentOpen-source AI agent framework by Nous Research. Executes customer triage, CRM tagging, and automated flows autonomously.
Supported Messaging & Customer Channels
Connect your channels in ChatbotX once, then automate customer conversations to any of them via your AI assistant.