Mochow MCP Server Python

🚀 Baidu Vector Database MCP Server

This code repository contains an MCP server that provides access to the features of Baidu Cloud Vector Database.

🚀 Quick Start

✅ Prerequisites

Before using the Baidu Cloud Vector Database MCP Server, ensure that you meet the following requirements:

1. Python 3.10 or higher.
2. uv installed to run the MCP Server.

📦 Installation

The recommended way to use the Baidu Cloud Vector Database MCP Server is to run it via uv without installation.

Clone the code repository and execute the following commands:

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

Subsequently, you can directly run it via uv, where you can modify endpoint and api-key as needed:

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

Alternatively, modify the .env file in the src/mochow_mcp_server/ directory to set environment variables, and then use the following command to run the server:

uv run src/mochow_mcp_server/server.py 

💻 Usage Examples

Supported Applications

The Baidu Cloud Vector Database MCP Server can be used with various large language model applications that support the Model Context Protocol:

• Claude Desktop: A desktop application developed by Anthropic for Claude.
• Cursor: An AI code editor that supports MCP.
• Custom MCP Clients: Any application that implements the MCP client specification.

Usage in Claude Desktop

Download Claude Desktop from https://claude.ai. Open the configuration file of Claude Desktop. On macOS, the path is ~/Library/Application Support/Claude/claude_desktop_config.json. Add the following configuration:

{
    "mcpServers": {
        "mochow": {
            "command": "/PATH/TO/uv",
            "args": [
                "--directory",
                "/path/to/mochow-mcp-server-python/src/mochow_mcp_server",
                "run",
                "server.py",
                "--endpoint",
                "http://127.0.0.1:8287",
                "--api-key",
                "mochow"
            ]
        }
    }
}

Restart Claude Desktop.

Usage in Cursor

Cursor also supports the MCP tool. You can add the Baidu MCP Server to Cursor in two ways: Open Cursor Settings > Features > MCP in sequence, click the + Add New MCP Server button, and add the following configuration to mcp.json:

{
    "mcpServers": {
        "mochow": {
            "command": "/PATH/TO/uv",
            "args": [
                "--directory",
                "/path/to/mochow-mcp-server-python/src/mochow_mcp_server",
                "run",
                "server.py",
                "--endpoint",
                "http://127.0.0.1:8287",
                "--api-key",
                "mochow"
            ]
        }
    }
}

Restart Cursor or reload the window.

🔧 Technical Details

Available Tools

The Baidu Cloud Vector Database MCP Server provides the following tools:

Database Operations

• list_databases: List all Databases in the database.
• create_database: Create a new Database.
  • Parameters:
    • database_name: The name of the Database to be created.
• use_database: Switch to an existing Database.
  • Parameters:
    • database_name: The name of the Database to switch to.

Table Operations

• list_tables: List all Tables in the database.
• describe_table: Get detailed information about a specified Table.
  • Parameters:
    • table_name: The name of the Table.
• stats_table: Get statistical information about a specified Table.
  • Parameters:
    • table_name: The name of the Table.

Data Operations

• delete_table_rows: Delete data using a filter expression.
  • Parameters:
    • table_name: The name of the Table.
    • filter_expr: The filter expression.
• select_table_rows: Query data using a filter expression.
  • Parameters:
    • table_name: The name of the Table.
    • filter_expr: The filter expression.
    • limit: The maximum number of query results.
    • output_fields: The names of the fields to be returned in the query results.

Index Operations

• create_vector_index: Create a vector index on a specified vector field.
  • Parameters:
    • table_name: The name of the Table.
    • index_name: The name of the vector index.
    • field_name: The name of the vector field.
    • index_type: The type of the vector index.
    • metric_type: The distance metric of the vector index.
    • params: The creation parameters of the vector index.
• rebuild_vector_index: Rebuild a specified vector index.
  • Parameters:
    • table_name: The name of the Table.
    • index_name: The name of the vector index.
• drop_vector_index: Delete a specified vector index.
  • Parameters:
    • table_name: The name of the Table.
    • index_name: The name of the vector index.
• describe_index: Get detailed information about a specified index.
  • Parameters:
    • table_name: The name of the Table.
    • index_name: The name of the vector index.

Retrieval Operations

• vector_search: Perform vector similarity retrieval with scalar filtering.
  • Parameters:
    • table_name: The name of the Table.
    • vector: The vector.
    • vector_field: The name of the vector field.
    • limit: The number of records to return in the similarity retrieval results that are closest to the target vector.
    • filter_expr: The filter expression.
    • output_fields: The names of the fields to be returned in the query results.
• fulltext_search: Perform full-text retrieval.
  • Parameters:
    • table_name: The name of the Table.
    • index_name: The name of the vector index.
    • search_text: The retrieval expression for full-text retrieval.
    • limit: The number of entries with the highest relevance to return in the full-text retrieval.
    • filter_expr: The filter expression.
    • output_fields: The names of the fields to be returned in the query results.

Environment Variables

• MOCHOW_ENDPOINT: The URI of the Baidu Cloud Vector Database connection instance.
• MOCHOW_API_KEY: The API key of the Baidu Cloud Vector Database instance.

💻 Usage Examples

Using Claude Desktop

Example 1: List all Databases in the database

How many databases do i have in the mochow db?

Claude will use the list_databases provided by the Baidu Cloud Vector Database MCP Server to obtain the database list.

Let me check how many databases you have in the Mochow instance.

You have 2 databases in your Mochow instance:

1. book
2. test

Example 2: View the schema information of a specified table

I want to get the detail of  table named book_segments in database book.

Claude will use the describe_table provided by the Baidu Cloud Vector Database MCP Server to obtain the detailed information of the table.

I'll help you get the details of the "book_segments" table in the "book" database. Let me first switch to the "book" database and then describe the table.

Here's the information about the "book_segments" table in the "book" database:

Database: book
Table Name: book_segments
Creation Time: 2025-05-06 11:08:22
State: NORMAL

Schema:

id (STRING)
Primary Key: Yes
Partition Key: Yes
Not Null: Yes

bookName (STRING)
Not Null: Yes

author (STRING)
Not Null: No

page (UINT32)
Not Null: No

segment (TEXT)
Not Null: No

vector (FLOAT_VECTOR)
Not Null: Yes
Dimension: 1024

Indexes
book_name_filtering_idx (FILTERING_INDEX)
Field: bookName
Order: ASCEND
Structure Type: DEFAULT

vector_idx (HNSW)
Field: vector
Metric Type: L2
Auto Build: False
Parameters: (M: 16 efConstruction: 200)