MCP Toolbox SDK Python

v1.0.0Databasesstable

Python SDK for interacting with the MCP Toolbox for Databases.

databasesgenailangchainlangchain-pythonllamaindex
Share:
185
Stars
0
Downloads
0
Weekly
0/5

What is MCP Toolbox SDK Python?

MCP Toolbox SDK Python is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python sdk for interacting with the mcp toolbox for databases.

Python SDK for interacting with the MCP Toolbox for Databases.

This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Python SDK for interacting with the MCP Toolbox for Database

Use Cases

Database interactions via Python
LangChain and LlamaIndex integration
GenAI database operations
googleapis

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-toolbox-sdk-python

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Toolbox SDK Python

The MCP Toolbox SDK for Python is a collection of Python packages that connect popular AI orchestration frameworks — LangChain, LlamaIndex, and Google ADK — to a running MCP Toolbox for Databases server. It translates MCP tool definitions into native framework objects, so database tools registered in the Toolbox server can be called as standard Python functions inside LangChain chains, LlamaIndex agents, or ADK workflows. Developers building AI agents that need structured, governed access to databases use this SDK to avoid writing custom MCP client code in each framework.

Prerequisites

  • Python 3.9 or later
  • A running MCP Toolbox for Databases server (see https://mcp-toolbox.dev for setup)
  • The appropriate Python package for your framework: toolbox-core, toolbox-langchain, toolbox-llamaindex, or toolbox-adk
  • Framework dependencies already installed (LangChain, LlamaIndex, or Google ADK depending on which SDK you use)
1

Set up and start the MCP Toolbox server

Before using the SDK, you need a running MCP Toolbox for Databases server. Follow the official getting-started guide at https://mcp-toolbox.dev/documentation/ to deploy it and register your database tools.

2

Install the appropriate SDK package for your framework

Choose the package that matches your AI framework. toolbox-core works in any Python code, while the framework-specific packages add native integration objects.

# Framework-agnostic
pip install toolbox-core

# LangChain / LangGraph
pip install toolbox-langchain

# LlamaIndex
pip install toolbox-llamaindex

# Google ADK
pip install toolbox-adk
3

Load tools from the Toolbox server

Connect to your running Toolbox server and load the registered tools. The SDK returns framework-native tool objects ready to use in your agent or chain.

from toolbox_langchain import ToolboxClient

# Connect to MCP Toolbox server
client = ToolboxClient("http://localhost:5000")

# Load all tools or a specific subset
tools = client.load_toolset()  # all tools
# tools = client.load_tool("search_products")  # single tool
4

Integrate tools into your agent or chain

Pass the loaded tools directly to your LangChain agent, LlamaIndex agent, or ADK workflow. The SDK handles all MCP protocol communication transparently.

from langchain.agents import initialize_agent
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o")
agent = initialize_agent(tools, llm, agent="zero-shot-react-description")
agent.run("Find all products with price under $50")
5

Run and verify database operations

Execute your agent and verify it correctly calls the Toolbox-registered database tools. The Toolbox server enforces access control and query governance defined in your tool configurations.

MCP Toolbox SDK Python Examples

LangChain agent using Toolbox tools

Complete example of loading MCP Toolbox tools into a LangChain agent. Assumes the Toolbox server is running at localhost:5000.

{
  "note": "This SDK is used in Python code, not as a standalone MCP server config.",
  "example": "See installation steps for Python usage pattern.",
  "toolbox_server_url": "http://localhost:5000",
  "packages": {
    "langchain": "toolbox-langchain",
    "llamaindex": "toolbox-llamaindex",
    "adk": "toolbox-adk",
    "core": "toolbox-core"
  }
}

Prompts to try

Once the Toolbox SDK is integrated into your agent, these are the kinds of natural-language database queries your agent can execute.

- "Search the products database for all items in the 'electronics' category"
- "Find the top 10 customers by total order value in the last 30 days"
- "Insert a new record into the inventory table with these details"
- "Run a semantic search over the knowledge base for documents about refund policies"
- "List all pending orders placed in the last 24 hours"

Troubleshooting MCP Toolbox SDK Python

Connection refused when calling client.load_toolset()

Verify the MCP Toolbox server is running and accessible at the URL you passed to ToolboxClient. The server must be started and have tools registered before the SDK can load them. Check the Toolbox server logs for startup errors.

ImportError when importing toolbox-langchain or toolbox-llamaindex

Ensure you have installed both the toolbox package and the underlying framework package. For example, toolbox-langchain requires langchain to already be installed. Run pip install langchain toolbox-langchain to install both.

Tools load successfully but the agent returns wrong or empty results

The tool behavior and allowed queries are governed by the tool definitions on the Toolbox server side, not the SDK. Review your Toolbox server tool configuration, verify the database connection, and check the server logs for query errors.

Frequently Asked Questions about MCP Toolbox SDK Python

What is MCP Toolbox SDK Python?

MCP Toolbox SDK Python is a Model Context Protocol (MCP) server that python sdk for interacting with the mcp toolbox for databases. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Toolbox SDK Python?

Follow the installation instructions on the MCP Toolbox SDK Python GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Toolbox SDK Python?

MCP Toolbox SDK Python works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Toolbox SDK Python free to use?

Yes, MCP Toolbox SDK Python is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-toolbox-sdk-python": { "command": "npx", "args": ["-y", "mcp-toolbox-sdk-python"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Toolbox SDK Python?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides