HomeDocumentation

MCP Server Integration

ChatReact implements the Model Context Protocol (MCP), allowing you to connect your ChatReact account to AI assistants like Claude Desktop, Cursor, and other MCP-compatible tools.

What is MCP?

The Model Context Protocol is an open standard that enables AI assistants to interact with external services and data sources. With ChatReact's MCP integration, you can:

  • Manage chatbots — update instructions, personality, and widget settings
  • Create and update FAQs using natural language
  • View analytics, chat history, and leads
  • Review Improvement Agent proposals and approve or reject them
  • Monitor live chat sessions and the waiting queue

Getting Started

1. Generate an API Key

  1. Navigate to your DashboardCompanyAPI tab
  2. Click Create API Key
  3. Give your key a descriptive name (e.g., "Claude Desktop") and select at least one permission
  4. Copy the generated key (starts with cr_)

API keys are available on paid plans — see our Pricing page.

Store your API key securely. It cannot be retrieved after creation.

2. Configure Your MCP Client

The ChatReact MCP server is hosted at https://www.chatreact.ai/api/mcp and communicates over HTTP (JSON-RPC). Authenticate with an Authorization: Bearer header — an X-API-Key header with the same key is also accepted.

Cursor IDE

Cursor supports remote MCP servers directly. Add to your Cursor MCP settings:

{
  "mcpServers": {
    "chatreact": {
      "url": "https://www.chatreact.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer cr_your_api_key_here"
      }
    }
  }
}

Claude Desktop

Claude Desktop's configuration file supports command-based servers, so use the standard mcp-remote bridge to connect to the hosted endpoint:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "chatreact": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://www.chatreact.ai/api/mcp",
        "--header",
        "X-API-Key:cr_your_api_key_here"
      ]
    }
  }
}

This setup requires Node.js to be installed. The example uses the X-API-Key header because some clients don't handle spaces in arguments reliably.

3. Restart Your AI Assistant

After saving the configuration, restart Claude Desktop or Cursor to establish the connection.

Available Tools

ChatReact MCP provides a comprehensive set of tools organized into categories:

Your Account

ToolDescription
user_profileGet your profile information
user_companiesList the company your API key is scoped to
user_notificationsGet your recent notifications

Company & Team Management

ToolDescription
company_listList the company your API key is scoped to
company_getGet details of a specific company
company_members_listList company members with their roles
company_chatbots_listList all chatbots for a company
company_updateUpdate company name, description, or settings

Chatbot Management

ToolDescription
chatbot_listList all chatbots with summary statistics
chatbot_getGet chatbot details and configuration
chatbot_get_instructionsGet core instructions for a chatbot
chatbot_add_instructionAdd a new core instruction
chatbot_update_instructionUpdate an existing core instruction
chatbot_delete_instructionDelete a core instruction
chatbot_update_personalityUpdate tonality, language, and messages
chatbot_toggle_activeActivate or deactivate a chatbot
chatbot_toggle_learningEnable or disable the learning phase
widget_settings_getGet the current widget settings
widget_settings_updateUpdate widget appearance (colors, size, position)

FAQ Management

ToolDescription
faq_listList all FAQs for a chatbot
faq_getGet FAQ details
faq_createCreate a new FAQ
faq_updateUpdate an existing FAQ
faq_deleteDelete an FAQ
faq_categories_listList FAQ categories
faq_suggestions_listList pending FAQ suggestions generated from chat conversations

Knowledge Base

ToolDescription
knowledge_documents_listList documents in a chatbot's knowledge base
knowledge_document_getGet details of a specific document
knowledge_document_deleteDelete a document from the knowledge base
knowledge_statsGet knowledge base statistics

Website crawling is managed from the dashboard — see Knowledge Base.

Lead Management

ToolDescription
lead_listList leads with optional filtering by status or category
lead_getGet full lead details including the source chat session
lead_updateUpdate a lead's status, category, or notes
lead_deleteDelete a lead permanently
lead_categories_listList lead categories
lead_statsGet lead statistics including counts by status
lead_field_config_getGet the lead capture field configuration

Chat History

ToolDescription
chat_sessions_listList chat sessions with optional filters
chat_session_getGet a chat session with all its messages
chat_session_searchSearch chat sessions by message content or visitor info

Analytics

ToolDescription
analytics_overviewGet chat counts, message counts, and satisfaction rates
analytics_chat_volumeGet chat volume over time for charts and trends

Improvement Agent

ToolDescription
improvement_sessions_listList improvement sessions
improvement_session_getGet session details including proposals
improvement_proposals_pendingList pending proposals awaiting review
improvement_proposal_approveApprove a proposal and apply the change
improvement_proposal_rejectReject a proposal

Live Chat

ToolDescription
live_chat_sessions_listList live chat sessions
live_chat_session_getGet a live chat session with all messages
live_chat_queueGet sessions waiting for an agent

Live chat tools are read-only. To chat with visitors directly, use the Live Chat dashboard.

Example Workflows

Adding a Core Instruction

Ask your AI assistant:

"Add a core instruction to my 'Support Bot' chatbot: we offer free shipping on orders over €50"

The assistant will use chatbot_add_instruction with appropriate parameters.

Reviewing Improvement Suggestions

"Show me all pending improvement proposals for my chatbot and explain what changes they suggest"

The assistant will:

  1. Use improvement_proposals_pending to fetch proposals
  2. Analyze and summarize each suggestion
  3. Approve or reject them on your behalf with improvement_proposal_approve or improvement_proposal_reject

Analyzing Chat Performance

"Give me a weekly report of chat volume and customer satisfaction for my chatbot"

The assistant will use analytics_overview and analytics_chat_volume to compile a comprehensive report.

Security

  • API keys are scoped to your company
  • Keys can be revoked at any time from the dashboard
  • API access is available on paid plans — see our Pricing page

Troubleshooting

Connection Failed

  1. Verify your API key is correct
  2. Check that the key hasn't been revoked
  3. Make sure your plan includes API access
  4. Restart your MCP client

Tool Not Found

Restart your MCP client after changing the configuration so it reloads the available tools. Tool names are lowercase with underscores (e.g., faq_list).


Need help? Contact our support team →