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 directly from your AI assistant
Create and update FAQs using natural language
View analytics and chat history
Control the Improvement Agent for chatbot optimization
Handle live chat sessions without leaving your AI tool

Getting Started

1. Generate an API Key

Navigate to your Dashboard → Settings → API Keys
Click Create API Key
Give your key a descriptive name (e.g., "Claude Desktop")
Copy the generated key (starts with cr_)

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

2. Configure Your MCP Client

Claude Desktop

Add the following to your Claude Desktop configuration file:

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

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

Cursor IDE

Add to your Cursor MCP settings:

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

Local Development (stdio)

For local development, you can use our npm package:

npm install -g @chatreact/mcp

Configure in your MCP client:

{
  "mcpServers": {
    "chatreact": {
      "command": "chatreact-mcp",
      "args": ["--api-key", "cr_your_api_key_here"]
    }
  }
}

3. Restart Your AI Assistant

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

Available Tools

ChatReact MCP provides over 30 tools organized into categories:

Company & Team Management

Tool	Description
`company_list`	List all companies you have access to
`company_get`	Get details of a specific company
`company_team_list`	List team members of a company

Chatbot Management

Tool	Description
`chatbot_list`	List all chatbots in a company
`chatbot_get`	Get chatbot details and configuration
`chatbot_create`	Create a new chatbot
`chatbot_update`	Update chatbot settings
`chatbot_get_instructions`	Get core instructions for a chatbot
`chatbot_add_instruction`	Add a new core instruction

FAQ Management

Tool	Description
`faq_list`	List all FAQs for a chatbot
`faq_get`	Get FAQ details
`faq_create`	Create a new FAQ
`faq_update`	Update an existing FAQ
`faq_delete`	Delete an FAQ
`faq_categories_list`	List FAQ categories
`faq_suggest`	Generate AI-suggested FAQs

Knowledge Base

Tool	Description
`knowledge_list_documents`	List uploaded documents
`knowledge_list_websites`	List crawled websites
`knowledge_crawl_website`	Start a website crawl
`knowledge_get_crawl_status`	Check crawl progress

Analytics

Tool	Description
`analytics_overview`	Get overall performance metrics
`analytics_chat_volume`	Get chat volume over time
`analytics_feedback`	Get feedback and ratings
`analytics_chat_history`	Browse chat sessions
`analytics_get_session`	Get detailed session data

Improvement Agent

Tool	Description
`improvement_list_sessions`	List improvement sessions
`improvement_start_session`	Start a new analysis session
`improvement_list_proposals`	List improvement proposals
`improvement_get_proposal`	Get proposal details
`improvement_create_proposal`	Create a custom proposal
`improvement_simulate_proposal`	Preview proposal effects
`improvement_apply_proposal`	Apply a proposal
`improvement_reject_proposal`	Reject a proposal

Live Chat

Tool	Description
`livechat_get_queue`	Get waiting chat sessions
`livechat_get_active_sessions`	List active human agent sessions
`livechat_get_session`	Get session details
`livechat_assign_session`	Assign yourself to a session
`livechat_send_message`	Send a message as agent
`livechat_close_session`	Close a chat session
`livechat_check_availability`	Check agent availability

Example Workflows

Creating a New Chatbot

Ask your AI assistant:

"Create a new chatbot called 'Support Bot' for my company 'acme-corp' with a friendly, professional tone"

The assistant will use chatbot_create with appropriate parameters.

Reviewing Improvement Suggestions

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

The assistant will:

Use improvement_list_proposals to fetch proposals
Analyze and summarize each suggestion
Help you decide which to apply

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_feedback to compile a comprehensive report.

Security

API keys are scoped to your user account and company access
All requests are logged in the audit trail
Keys can be revoked at any time from the dashboard
Rate limits apply: 60 requests/minute

Troubleshooting

Connection Failed

Verify your API key is correct
Check that the key hasn't been revoked
Ensure you have an active internet connection
Restart your MCP client

Tool Not Found

Some tools require specific permissions. Ensure you have the appropriate role in the company (Owner, Admin, or Manager).

Rate Limited

If you see rate limit errors, wait a minute before retrying. Consider batching operations when possible.

Need help? Contact our support team →