home / mcp / baidu vector database mcp server

Baidu Vector Database MCP Server

Model Context Protocol Server for Mochow

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "baidu-mochow-mcp-server-python": {
      "command": "uv",
      "args": [
        "run",
        "src/mochow_mcp_server/server.py",
        "--endpoint",
        "http://127.0.0.1:8287",
        "--api-key",
        "mochow"
      ],
      "env": {
        "MOCHOW_API_KEY": "mochow",
        "MOCHOW_ENDPOINT": "http://127.0.0.1:8287"
      }
    }
  }
}

You run a Baidu Cloud Vector Database MCP Server locally to access vector data and perform operations from your preferred MCP-enabled applications. This server translates your MCP requests into actions on the Baidu Cloud Vector Database, enabling seamless integration with large language model workflows and custom clients.

How to use

Start the MCP Server locally using an MCP client. The server is designed to be run via the UV tool, and you can point it at your endpoint and API key to begin handling requests from your MCP-based applications.

How to install

Prerequisites: You need Python 3.10 or newer and the UV tool installed on your system.

Clone the MCP server repository and enter the project directory.

Commands you will run:

git clone https://github.com/baidu/mochow-mcp-server-python.git
cd mochow-mcp-server-python

Additional setup and run options

You can start the server directly with UV, which runs the server script without a formal install step.

Two common ways to start the server are:

uv run src/mochow_mcp_server/server.py
uv run src/mochow_mcp_server/server.py --endpoint http://127.0.0.1:8287 --api-key mochow

Environment and configuration

If you prefer, you can configure environment variables in the local environment. The following variables are used to connect to the Baidu Cloud Vector Database:

MOCHOW_ENDPOINT=http://127.0.0.1:8287
MOCHOW_API_KEY=YOUR_API_KEY

Available tools

list_databases

List all Database instances available in the connected Baidu Cloud Vector Database.

create_database

Create a new Database with a specified name.

use_database

Switch the active context to a specified Database.

list_tables

List all Tables within the current Database.

describe_table

Get detailed information about a specific Table, including schema and properties.

stats_table

Retrieve statistical information for a given Table.

delete_table_rows

Delete rows from a Table using a filter expression.

select_table_rows

Query rows from a Table using a filter expression and limit.

create_vector_index

Create a vector index on a specified field with a given type and parameters.

rebuild_vector_index

Rebuild a specified vector index for a Table.

drop_vector_index

Delete a specified vector index from a Table.

describe_index

Retrieve details about a specific vector index.

vector_search

Perform a vector similarity search with optional scalar filters and field selection.

fulltext_search

Execute a full-text search against a Table using a specified index and filter.