Integrate seekdb MCP Server with Cline

seekdb provides capabilities for storing vector data, building vector indexes, and performing embedding vector searches. You can store vectorized data in seekdb for subsequent searches.

Cline is an open-source AI coding assistant that supports the MCP protocol.

This topic demonstrates how to quickly build a backend application using seekdb MCP Server and Cline.

Prerequisites

• You have deployed the seekdb database.

• Install Python 3.11 or later and the corresponding pip. If your machine has a low Python version, you can use Miniconda to create a new Python 3.11 or later environment. For more information, see Miniconda installation guide.

• Install the Python package manager uv. After the installation is complete, run the uv --version command to verify whether the installation is successful:

  pip install uv
  uv --version

• Install Cline:

  • If you use the Visual Studio Code IDE, search for and install the Cline plugin in the Extensions section. The plugin name is Cline.

  • If you do not use an IDE, refer to the Cline installation guide and download Cline from Cline.

Step 1: Obtain the database connection information

Contact the seekdb database deployment personnel or administrator to obtain the corresponding database connection string, for example:

mysql -h$host -P$port -u$user_name -p$password -D$database_name

Parameter description:

• $host: the IP address for connecting to seekdb.

• $port: the port for connecting to seekdb. The default value is 2881.

• $database_name: the name of the database to be accessed.

  tip

  The user for the connection must have the CREATE, INSERT, DROP, and SELECT permissions on the database.

• $user_name: the database connection account.

• $password: the account password.

Step 2: Configure seekdb MCP Server

This example uses Visual Studio Code to show how to configure seekdb MCP Server.

Install seekdb MCP Server

Run the following command to install seekdb MCP Server:

pip install seekdb-mcp-server

Configure the seekdb server environment variables in the .env file

Create a file named .env in the current directory and add the following content:

vi .env

SEEKDB_HOST=localhost      # Database host
SEEKDB_PORT=2881           # Database port (default: 2881)
SEEKDB_USER=your_username
SEEKDB_PASSWORD=your_password
SEEKDB_DATABASE=your_database

Start in SSE mode

env $(cat .env | xargs) uvx seekdb-mcp-server --transport sse --port 8000 --host 0.0.0.0

Create a Visual Studio Code workspace

Manually create a Visual Studio Code workspace on your local device and open it with Visual Studio Code. The files generated by Cline will be stored in this directory. The example directory name is cline-generate.

Configure the large model

Click the Cline icon in the sidebar to open the Cline dialog box and configure a large model for Cline:

Configure seekdb MCP Server

1. Click the MCP Servers icon in the following figure.

   

2. Fill in the configuration file and click OK.

   {
     "mcpServers": {
       "sse-seekdb": {
         "autoApprove": [],
         "disabled": false,
         "timeout": 60,
         "type": "sse",
         "url": "http://ip:port/sse"
       }
     }
   }

3. If the configuration is successful, the status will show as Available, and the MCP tools and resources information will be displayed, as shown below:

   

Test the MCP Server

Open the Cline session box as shown below, and enter the prompt How many tables in the test database?. Cline will display the SQL statement to be executed. If there are no issues, click Approve. Cline will display the names of the tables in the current test database, indicating that it can connect to seekdb.

Use FastAPI to quickly create a RESTful API project

You can use FastAPI to quickly create a RESTful API project. FastAPI is a Python web framework that allows you to build RESTful APIs quickly.

1. Create a customer table

   Enter the prompt: Create a "customer" table with "ID" as the primary key and containing fields such as "name", "age", "telephone", and "location" in the dialog box. Confirm the SQL statement and click the Approve button to execute it.

   

2. Insert test data

   Enter the prompt: Insert 10 pieces of data into the customer table in the dialog box. Confirm the SQL statement and click the Approve button to execute it.

   

3. Create a FastAPI project

   Enter the prompt: Create a FastAPI project on the customer table in the dialog box and click the Approve button to execute it.

   

   This step will automatically generate multiple files. It is recommended to select "Accept All" for the first use, as the content of the AI-generated files may be uncertain. You can adjust them as needed based on your actual requirements later.

4. Configure the database connection information for the FastAPI project

   

5. Install the project dependencies

   Run the following command to install the project dependencies:

   pip install -r requirements.txt

6. Start the FastAPI project

   Run the following command to start the FastAPI project:

   source .env
   uvicorn main:app --reload

7. View the data in the table

   Run the following command in the command line or use other request tools to view the data in the table:

   curl http://127.0.0.1:8000/customers

   The returned result is as follows:

   [{"name":"John Smith","age":35,"telephone":"13800138001","location":"New York","id":1},{"name":"Sarah Johnson","age":28,"telephone":"13800138002","location":"Los Angeles","id":2},{"name":"Michael Brown","age":42,"telephone":"13800138003","location":"Chicago","id":3},{"name":"Emily Davis","age":31,"telephone":"13800138004","location":"Houston","id":4},{"name":"David Wilson","age":39,"telephone":"13800138005","location":"Phoenix","id":5},{"name":"Lisa Miller","age":26,"telephone":"13800138006","location":"Philadelphia","id":6},{"name":"James Taylor","age":45,"telephone":"13800138007","location":"San Antonio","id":7},{"name":"Jennifer Anderson","age":33,"telephone":"13800138008","location":"San Diego","id":8},{"name":"Robert Thomas","age":37,"telephone":"13800138009","location":"Dallas","id":9},{"name":"Mary Jackson","age":29,"telephone":"13800138010","location":"San Jose","id":10}]