Focus_mcp_data: Smart Conversations & Instant Insights

Focus_mcp_data turns complex data queries into smooth multi-round ChatBI conversations – plug in, chat smartly, and unlock insights effortlessly." )

Visit Repository

✨ Research And Data

4.3(66 reviews)

99 saves

46 comments

44% of users reported increased productivity after just one week

About Focus_mcp_data

What is Focus_mcp_data: Smart Conversations & Instant Insights?

Focus_mcp_data is a middleware solution enabling AI-driven systems to interact with structured datasets through natural language queries. It acts as a bridge between machine learning models and database infrastructures, providing real-time analytical capabilities. By leveraging advanced parsing algorithms, it transforms user intent into precise data operations, delivering actionable insights without manual coding interventions.

How to use Focus_mcp_data: Smart Conversations & Instant Insights?

Install dependencies: JDK 17+ and Gradle 7.4+
Configure server parameters in config.yaml with your DataFocus API credentials
Deploy via gradle bootRun for development environments
Integrate REST endpoints into your application using standardized JSON schemas

Focus_mcp_data Features

Key Features of Focus_mcp_data: Smart Conversations & Instant Insights?

Context-aware query optimization: Automatically detects aggregation requirements in user requests
Multi-tenancy support: Securely manages concurrent data sources through isolated execution contexts
Interactive feedback loop: Provides query disambiguation prompts for ambiguous requests
Performance dashboards: Real-time monitoring of query latency and resource utilization

Use cases of Focus_mcp_data: Smart Conversations & Instant Insights?

Common applications include:

Financial Analysis

"Show Q3 revenue variance by product segment" → Automatic generation of comparative pivot tables

Operational Intelligence

"Identify underperforming stores with inventory turnover < 1.2" → Immediate SQL query generation with performance thresholds

Focus_mcp_data FAQ

FAQ from Focus_mcp_data: Smart Conversations & Instant Insights?

Does it support NoSQL databases?: Yes, through MongoDB and Cassandra adapters available in v2.1+
How is data security ensured?: All queries are encrypted using TLS 1.3 and role-based access controls
What's the average query response time?: Typically 180-320ms for datasets under 50GB, with caching optimizations

Content

FOCUS DATA MCP Server [中文]

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

Features

Register on DataFocus to open an application space, and import (directly connect to) the data tables to be analyzed.
Select Datafocus data table initialization dialogue
Natural language data acquisition results

Prerequisites

jdk 23 or higher. Download jdk
gradle 8.12 or higher. Download gradle
register Datafocus to obtain bearer token:
1. Register an account in Datafocus
2. Create an application
3. Enter the application
4. Admin -> Interface authentication -> Bearer Token -> New Bearer Token

Installation

Clone this repository:

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

Build the server:


The jar path: 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`):

```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 table list in datafocus.

**Parameters:**

  * `name` (optional): table name to filter
  * `bearer` (required): bearer token

**Example:**

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

### 2\. gptText2DataInit

Initialize dialogue.

**Parameters:**

  * `names` (required): selected table names
  * `bearer` (required): bearer token
  * `language` (optional): language ['english','chinese']

**Example:**

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

### 3\. gptText2DataData

Query data results.

**Parameters:**

  * `chatId` (required): chat id
  * `input` (required): Natural language
  * `bearer` (required): bearer token

**Example:**

```json { "chatId": "03975af5de4b4562938a985403f206d4", "input": "max(age)", "bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU=" } ```

## Response Format

All tools return responses in the following format:

```json { "errCode": 0, "exception": "", "msgParams": null, "promptMsg": null, "success": true, "data": { } } ```

## Visual Studio Code Cline Sample

  1. vsCode install cline plugin
  2. mcp server config ![config mcp server](./mcp_server_config.png)
  3. use 
    1. get table list ![get table list1](./focus_mcp_data_table_1.png) ![get table list2](./focus_mcp_data_table_2.png)
    2. Initialize dialogue ![Initialize dialogue](./focus_mcp_data_init.png)
    3. query: what is the sum salary ![query](./focus_mcp_data_data.png)

## Contact：

[https://discord.gg/mFa3yeq9](https://discord.gg/mFa3yeq9) ![Datafocus](./wechat-qrcode.png)