Focus MCP Data

The intelligent data query plugin under DataFocus that supports multi-round conversations provides plug-and-play ChatBI capabilities.

java

14

GitHub Stars

java

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "focussearch-focus_mcp_data": {
      "command": "java",
      "args": [
        "-jar",
        "path/to/focus_mcp_data/focus_mcp_data.jar"
      ]
    }
  }
}

You can use the MCP server to query data results from DataFocus with natural language. This server connects to your data tables, initializes a dialogue, and returns data results in an interactive, natural-language way so you can extract insights without writing complex queries.

How to use

To start using this MCP server, run the local Java-based MCP process and connect it to your DataFocus data tables. You will first initialize the dialogue with the tables you want to analyze, then you can ask natural-language questions about the data and receive results.

How to install

Prerequisites: ensure you have Java Development Kit (JDK) 23 or newer installed on your system.

Prerequisites: ensure you have Gradle 8.12 or newer installed on your system.

Install steps to obtain and run the MCP server locally.

# 1) Clone the MCP server repository
git clone https://github.com/FocusSearch/focus_mcp_data.git
cd focus_mcp_data

# 2) Build the server
gradle clean
gradle bootJar

# The runnable jar is created at
# build/libs/focus_mcp_data.jar

Configuration and usage notes

The MCP server is configured to run as a local stdio-based server using Java. The configuration snippet below shows how to run the server and what tools to auto-approve after startup.

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

Additional tips

You will need a bearer token from DataFocus to access the data tables. Use the DataFocus interface to create an application and generate a Bearer Token for authentication.
After you start the MCP server, you can list available tables, initialize the dialogue with your chosen tables, and then query for data results using natural language such as questions about sums, averages, or specific column analyses.

Available tools

tableList

Retrieves the list of DataFocus tables available for analysis. Requires bearer token for authentication.

gptText2DataInit

Initializes the dialogue by selecting one or more table names to work with and setting optional language preferences.

gptText2DataData

Queries data results using natural language input and returns the analysis or computed results for the selected tables.