Alibaba Cloud Lindorm MCP server

The Lindorm MCP Server provides an interface for connecting to Lindorm, a multi-model NoSQL database from Alibaba Cloud. It allows you to interact with Lindorm's wide-table engine, search-engine, vector-engine, and AI-engine through a standardized Model Context Protocol (MCP) server.

Prerequisites for Lindorm Configuration

Before setting up the MCP server, you need to:

• Purchase the Lindorm wide-table engine, search-engine, vector-engine, and AI-engine on Alibaba Cloud
• Deploy a text-embedding model by following the official instructions
• Create your index (knowledgebase) and import your data using the deployed embedding model

Installation and Setup

Environment Configuration

1. Clone the repository and navigate to the project directory
2. Create your environment file:

cp .env.example .env

3. Edit the .env file with your specific configuration:

LINDORM_INSTANCE_ID=your_instance_id
USING_VPC_NETWORK=true_or_false
USERNAME=your_username
PASSWORD=your_password
TEXT_EMBEDDING_MODEL=your_embedding_model_name
TABLE_DATABASE=your_database_name

Note: This configuration assumes all engines share the same username and password.

Running the MCP Server

First, install uv if you haven't already. Then install and run the MCP server:

cd /path/to/alibabacloud-lindorm-mcp-server/
uv pip install .
uv run python -m src.lindorm_mcp_server.server

Visual Studio Code Integration

1. Install the Cline extension
2. Create the .env file under /path/to/alibabacloud-lindorm-mcp-server/
3. Copy the MCP configuration from .vscode/mcp.json to cline_mcp_settings.json, replacing paths and variables as needed
4. Start the MCP server through the Cline extension

Available Tools and Usage

Vector and Full-Text Search

To retrieve data from an existing index using both full-text and vector search:

lindorm_retrieve_from_index

Parameters:

• index_name: The index or knowledgebase name
• query: The search query
• content_field: The text field that stores content
• vector_field: The vector field that stores the vector index
• top_k: Number of results to return

Index Management

To get field information from an index:

lindorm_get_index_fields

Parameters:

• index_name: The index or knowledgebase name

To list all available indexes:

lindorm_list_all_index

SQL Operations

To execute SQL queries on Lindorm:

lindorm_execute_sql

Parameters:

• query: SQL query starting with SELECT

To show all tables in the database:

lindorm_show_tables

To get a table's schema:

lindorm_describe_table

Parameters:

• table_name: The name of the table

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "lindorm-mcp-server" '{"command":"python","args":["-m","src.lindorm_mcp_server.server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "lindorm-mcp-server": {
            "command": "python",
            "args": [
                "-m",
                "src.lindorm_mcp_server.server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "lindorm-mcp-server": {
            "command": "python",
            "args": [
                "-m",
                "src.lindorm_mcp_server.server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect