Datafocus

🚀 FOCUS DATA MCP Server

The Model Context Protocol (MCP) server enables AI assistants to directly query data results. Users can obtain data from DataFocus using natural language.

✨ Features

• Register on DataFocus to open an application space and import (directly connect) the data tables to be analyzed.
• Select a Datafocus data table to initialize a conversation.
• Use natural language to get data results.

📋 Prerequisites

• JDK 23 or higher. Download JDK.
• Gradle 8.12 or higher. Download Gradle.
• Register on Datafocus to obtain a bearer token:
  1. Register an account on Datafocus.
  2. Create an application.
  3. Enter the application.
  4. Management -> Interface Authentication -> Bearer Token -> Create a new bearer token.

📦 Installation

1. Clone this repository:

git clone https://github.com/FocusSearch/focus_mcp_data.git
cd focus_mcp_data

2. Build the server:

gradle clean
gradle bootJar

The path of the generated JAR: build/libs/focus_mcp_data.jar

🔧 MCP Configuration

Add the server to your MCP settings file (usually located at ~/AppData/Roaming/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json):

{
  "mcpServers": {
    "focus_mcp_data": {
      "command": "java",
      "args": [
        "-jar",
        "path/to/focus_mcp_data/focus_mcp_data.jar"
      ],
      "autoApprove": [
        "tableList",
        "gptText2DataInit",
        "gptText2DataData"
      ]
    }
  }
}

💻 Available Tools

1. tableList

Get the list of forms in DataFocus.

Parameters:

• name (optional): Filter table names.
• bearer (required): Bearer token.

Example:

{
  "name": "test",
  "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}

2. gptText2DataInit

Initialize a conversation.

Parameters:

• names (required): Selected form names.
• bearer (required): Bearer token.
• language (optional): Language ['english', 'chinese'].

Example:

{
  "names": [
    "test1",
    "test2"
  ],
  "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}

3. gptText2DataData

Query data using natural language.

Parameters:

• question (required): User question.
• bearer (required): Bearer token.

Example:

{
  "question": "显示所有员工的信息",
  "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}

📄 Response Format

All API requests will return the following unified JSON format:

{
  "code": 200,          // Status code
  "message": "成功",    // Description information
  "data": {}            // Returned data
}

If an error occurs, the response will contain an error code and message.

💻 Usage Examples

Visual Studio Code

1. Configure the MCP settings file (as described above).
2. Run the server in the terminal:

java -jar build/libs/focus_mcp_data.jar

3. Interact using MCP tools.

Example Conversations

Query the table list

{
  "method": "tableList",
  "params": {
    "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
  }
}

Initialize a conversation

{
  "method": "gptText2DataInit",
  "params": {
    "names": ["test1", "test2"],
    "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
  }
}

Query data

{
  "method": "gptText2DataData",
  "params": {
    "question": "显示所有员工的信息",
    "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
  }
}

📞 Contact Information

https://discord.gg/mFa3yeq9