Lindorm

Provides MCP access to Lindorm SQL and vector search for knowledge bases and SQL operations.

python

GitHub Stars

python

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": {
    "aliyun-alibabacloud-lindorm-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "-m",
        "src.lindorm_mcp_server.server"
      ],
      "env": {
        "PASSWORD": "YOUR_LINDORM_PASSWORD",
        "USERNAME": "YOUR_LINDORM_USERNAME",
        "TABLE_DATABASE": "YOUR_TABLE_DATABASE",
        "USING_VPC_NETWORK": "true or false",
        "LINDORM_INSTANCE_ID": "YOUR_LINDORM_INSTANCE_ID",
        "TEXT_EMBEDDING_MODEL": "YOUR_EMBEDDING_MODEL"
      }
    }
  }
}

You deploy and run an MCP server to access Lindorm’s SQL and vector search capabilities through a unified MCP interface. This server lets you perform SQL operations on Lindorm wide tables, as well as text and vector searches, from a single MCP endpoint.

How to use

Connect with an MCP client to the Lindorm MCP Server to perform SQL queries against Lindorm wide tables and to run combined full-text and vector searches. You can retrieve index metadata, list available indexes, describe table schemas, and execute SQL queries, all through the MCP endpoints. Use the provided tools to fetch index fields, retrieve documents from an index, and execute SQL against your Lindorm database.

How to install

Prerequisites: you need Python available on your machine. You also need the UV runtime interface to start the MCP server.

Obtain the server files and navigate to the project directory.
Create your environment configuration file from the example.
Install and run the MCP server using the runtime commands shown here.

# Step 1: Change to the project directory (adjust path as needed)
cd /path/to/alibabacloud-lindorm-mcp-server/

# Step 2: Create your local environment configuration
cp .env.example .env

# Step 3: Start the MCP server using the UV runtime
uv pip install .
uv run python -m src.lindorm_mcp_server.server

Environment and configuration

Set up a local environment file with the following values. Replace placeholders with your actual Lindorm details.

LINDORM_INSTANCE_ID=YOUR_LINDORM_INSTANCE_ID
USING_VPC_NETWORK=true|false
USERNAME=YOUR_LINDORM_USERNAME
PASSWORD=YOUR_LINDORM_PASSWORD
TEXT_EMBEDDING_MODEL=YOUR_EMBEDDING_MODEL
TABLE_DATABASE=YOUR_TABLE_DATABASE

Available tools

lindorm_retrieve_from_index

Retrieve from an existing index/knowledgebase using both full-text search and vector search, and return aggregated results. Parameters include index_name, query, content_field, vector_field, and top_k.

lindorm_get_index_fields

Get field information for an index to identify content and vector fields. Parameters: index_name.

lindorm_list_all_index

List all available indexes/knowledgebases.

lindorm_execute_sql

Execute a SQL query against the Lindorm database. Parameters: query (SQL string starting with SELECT).

lindorm_show_tables

List all tables present in the Lindorm database.

lindorm_describe_table

Describe the schema of a specific table. Parameters: table_name.

Built by

VeilStrat

AI signals for GTM teams