FOCUS DATA MCP Server [Zhong Wen ]
A Model Context Protocol (MCP) server enables artificial intelligence assistants to convert natural language into SQL statements.
There are already so many Text-to-SQL frameworks. Why do we still need another one?
In simple terms, focus_mcp_sql adopts a two-step SQL generation solution, which enables control over the hallucinations of LLM and truly builds the trust of non-technical users in the generated SQL results.
Below is the comparison table between focus_mcp_sql and others:
Comparison Analysis Table
Here's a side-by-side comparison of focus_mcp_sql with other LLM-based frameworks:
| Feature | Traditional LLM Frameworks | focus_mcp_sql |
|---|---|---|
| Generation Process | Black box, direct SQL generation | Transparent, two-step (keywords + SQL) |
| Hallucination Risk | High, depends on model quality | Low, controllable (keyword verification) |
| Speed | Slow, relies on large model inference | Fast, deterministic keyword-to-SQL |
| Cost | High, requires advanced models | Low, reduces reliance on large models |
| Non-Technical User Friendliness | Low, hard to verify results | High, easy keyword checking |
Features
-Initialize the model -Convert natural language to SQL statements
Prerequisites
- jdk 23 or higher. Download jdk
- gradle 8.12 or higher. Download gradle
- register Datafocus to obtain bearer token:
- Register an account in Datafocus
- Create an application
- Enter the application
- Admin -> Interface authentication -> Bearer Token -> New Bearer Token
Installation
- Clone this repository:
git clone https://github.com/FocusSearch/focus_mcp_sql.git
cd focus_mcp_sql
cd focus_mcp_sql
- Build the server:
gradle clean
gradle bootJar
The jar path: build/libs/focus_mcp_sql.jar
gradle bootJar
The jar path: build/libs/focus_mcp_sql.jar
MCP Configuration
Add the server to your MCP settings file:
{
"mcpServers": {
"focus_mcp_data": {
"command": "java",
"args": [
"-jar",
"path/to/focus_mcp_sql/focus_mcp_sql.jar"
],
"autoApprove": [
"gptText2sqlStart",
"gptText2sqlChat"
]
}
}
}
"mcpServers": {
"focus_mcp_data": {
"command": "java",
"args": [
"-jar",
"path/to/focus_mcp_sql/focus_mcp_sql.jar"
],
"autoApprove": [
"gptText2sqlStart",
"gptText2sqlChat"
]
}
}
}
Available Tools
1. gptText2sqlStart
initial model.
Parameters:
model(required): table modelbearer(required): bearer tokenlanguage(optional): language ['english','chinese']
Example:
{
"model": {
"tables": [
{
"columns": [
{
"columnDisplayName": "name",
"dataType": "string",
"aggregation": "",
"columnName": "name"
},
{
"columnDisplayName": "address",
"dataType": "string",
"aggregation": "",
"columnName": "address"
},
{
"columnDisplayName": "age",
"dataType": "int",
"aggregation": "SUM",
"columnName": "age"
},
{
"columnDisplayName": "date",
"dataType": "timestamp",
"aggregation": "",
"columnName": "date"
}
],
"tableDisplayName": "test",
"tableName": "test"
}
],
"relations": [
],
"type": "mysql",
"version": "8.0"
},
"bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}
"model": {
"tables": [
{
"columns": [
{
"columnDisplayName": "name",
"dataType": "string",
"aggregation": "",
"columnName": "name"
},
{
"columnDisplayName": "address",
"dataType": "string",
"aggregation": "",
"columnName": "address"
},
{
"columnDisplayName": "age",
"dataType": "int",
"aggregation": "SUM",
"columnName": "age"
},
{
"columnDisplayName": "date",
"dataType": "timestamp",
"aggregation": "",
"columnName": "date"
}
],
"tableDisplayName": "test",
"tableName": "test"
}
],
"relations": [
],
"type": "mysql",
"version": "8.0"
},
"bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}
model Can Shu Shuo Ming :
| Ming Cheng | Wei Zhi | Lei Xing | Bi Xuan | Shuo Ming |
|---|---|---|---|---|
| model | body | object | Shi | none |
| >> type | body | string | Shi | Shu Ju Ku Lei Xing |
| >> version | body | string | Shi | Shu Ju Ku Ban Ben |
| >> tables | body | [object] | Shi | Biao Jie Gou Lie Biao |
| >>>> tableDisplayName | body | string | Fou | Biao Xian Shi Ming |
| >>>> tableName | body | string | Fou | Biao Yuan Shi Ming |
| >>>> columns | body | [object] | Fou | Biao Lie Lie Biao |
| >>>>>> columnDisplayName | body | string | Shi | Lie Xian Shi Ming |
| >>>>>> columnName | body | string | Shi | Lie Yuan Shi Ming |
| >>>>>> dataType | body | string | Shi | Lie Shu Ju Lei Xing |
| >>>>>> aggregation | body | string | Shi | Lie Ju He Fang Shi |
| >> relations | body | [object] | Shi | Biao Guan Lian Guan Xi Lie Biao |
| >>>> conditions | body | [object] | Fou | Guan Lian Tiao Jian |
| >>>>>> dstColName | body | string | Fou | dimension Biao Guan Lian Lie Yuan Shi Ming |
| >>>>>> srcColName | body | string | Fou | fact Biao Guan Lian Lie Yuan Shi Ming |
| >>>> dimensionTable | body | string | Fou | dimension Biao Yuan Shi Ming |
| >>>> factTable | body | string | Fou | fact Biao Yuan Shi Ming |
| >>>> joinType | body | string | Fou | Guan Lian Lei Xing |
2. gptText2sqlChat
Convert natural language to SQL.
Parameters:
chatId(required): chat idinput(required): Natural languagebearer(required): bearer token
Example:
{
"chatId": "03975af5de4b4562938a985403f206d4",
"input": "what is the max age",
"bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}
"chatId": "03975af5de4b4562938a985403f206d4",
"input": "what is the max age",
"bearer": "ZTllYzAzZjM2YzA3NDA0ZGE3ZjguNDJhNDjNGU4NzkyYjY1OTY0YzUxYWU5NmU="
}
Response Format
All tools return responses in the following format:
{
"errCode": 0,
"exception": "",
"msgParams": null,
"promptMsg": null,
"success": true,
"data": {
}
}
"errCode": 0,
"exception": "",
"msgParams": null,
"promptMsg": null,
"success": true,
"data": {
}
}