FOCUS DATA

A NL2SQL plugin based on FocusSearch keyword parsing, offering greater accuracy, higher speed, and more reliability!

java

38

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_sql": {
      "command": "java",
      "args": [
        "-jar",
        "path/to/focus_mcp_sql/focus_mcp_sql.jar"
      ]
    }
  }
}

You can use the Focus Data MCP Server to translate natural language queries into SQL statements through a two-step, controllable process. This server is designed to help AI assistants generate accurate SQL while reducing hallucinations and enabling non-technical users to verify results through clear keyword-to-SQL steps.

How to use

To get started, deploy the MCP server and connect it to your MCP client. You will first initialize the model with a defined schema, then convert natural language requests into SQL through a two-step process: (1) keyword extraction and verification, and (2) translation into SQL. Use the start/end flow to ensure deterministic results and easy auditing of the generated SQL. Practical usage patterns include querying specific tables, filtering data, aggregations, and joining related tables while keeping a clear trail from your natural language prompt to the final SQL.

How to install

# Prerequisites
- JDK 23 or higher
- Gradle 8.12 or higher

# Build and run
gradle clean
gradle bootJar

# The server runs from the generated JAR
# Ensure you use the path to your built JAR when configuring MCP

Additional setup and usage notes

Configure your MCP client to use the Focus Data MCP Server by pointing to the configured server entry. The server exposes a start endpoint that initializes the model and a chat/SQL path that converts natural language prompts into SQL. When you run the server, keep your bearer token secure and pass it to client requests as shown in the configuration example.

Available tools

gptText2sqlStart

Initial model to define table structures, relations, type, version, and bearer token for starting the text-to-SQL process.

gptText2sqlChat

Chat-based interface to convert natural language prompts into SQL queries using an ongoing chat session.