Repository files navigation

This repository contains Python SDKs designed to seamlessly integrate thefunctionalities of theMCPToolbox into your Gen AIapplications. These SDKs allow you to load tools defined in Toolbox and use themas standard Python functions or objects within popular orchestration frameworksor your custom code.

This simplifies the process of incorporating external functionalities (likeDatabases or APIs) managed by Toolbox into your GenAI applications.

• Overview
• Which Package Should I Use?
• Available Packages
• Getting Started
• Contributing
• License
• Support

The MCP Toolbox service provides a centralized way to manage and expose tools(like API connectors, database query tools, etc.) for use by GenAI applications.

These Python SDKs act as clients for that service. They handle the communication needed to:

• Fetch tool definitions from your running Toolbox instance.
• Provide convenient Python objects or functions representing those tools.
• Invoke the tools (calling the underlying APIs/services configured in Toolbox).
• Handle authentication and parameter binding as needed.

By using these SDKs, you can easily leverage your Toolbox-managed tools directlywithin your Python applications or AI orchestration frameworks.

Choosing the right package depends on how you are building your application:

• toolbox-langchain:Use this package if you are building your application using the LangChain orLangGraph frameworks. It provides tools that are directly compatible with theLangChain ecosystem (BaseTool interface), simplifying integration.
• toolbox-llamaindex:Use this package if you are building your application using the LlamaIndex framework.It provides tools that are directly compatible with theLlamaIndex ecosystem (BaseTool interface), simplifying integration.
• toolbox-core:Use this package if you are not using LangChain/LangGraph or any otherorchestration framework, or if you need a framework-agnostic way to interactwith Toolbox tools (e.g., for custom orchestration logic or direct use inPython scripts).

This repository hosts the following Python packages. See the package-specificREADME for detailed installation and usage instructions:

Package	Target Use Case	Integration	Path	Details (README)	PyPI Status
toolbox-core	Framework-agnostic / Custom applications	Use directly / Custom	packages/toolbox-core/	📄View README
toolbox-langchain	LangChain / LangGraph applications	LangChain / LangGraph	packages/toolbox-langchain/	📄View README
toolbox-llamaindex	LlamaIndex applications	LlamaIndex	packages/toolbox-llamaindex/	📄View README

To get started using Toolbox tools with an application, follow these general steps:

1. Set up and Run the Toolbox Service:

   Before using the SDKs, you need the main MCP Toolbox service running. Followthe instructions here:Toolbox Getting StartedGuide

2. Install the Appropriate SDK:

   Choose the package based on your needs (see "Which Package Should I Use?" above) and install it:

   # For the core, framework-agnostic SDKpip install toolbox-core# OR# For LangChain/LangGraph integrationpip install toolbox-langchain# For the LlamaIndex integrationpip install toolbox-llamaindex

3. Use the SDK:

   Consult the README for your chosen package (linked in the "AvailablePackages" section above) for detailed instructions onhow to connect the client, load tool definitions, invoke tools, configureauthentication/binding, and integrate them into your application orframework.

Contributions are welcome! Please refer to theCONTRIBUTING.mdto get started.

This project is licensed under the Apache License 2.0. See theLICENSE filefor details.

If you encounter issues or have questions, please check the existingGitHubIssues for the main Toolboxproject. If your issue is specific to one of the SDKs, please look for existingissueshere oropen a new issue in this repository.