About OpenAPITools SDK
OpenAPITools SDK is a Python package for creating and running tools with a shared interface across Anthropic Claude, OpenAI GPT, and LangChain. Developers can define tools in Python or Bash and execute them locally or through an API mode.
Key features
- 01Define tools in Python or Bash
- 02Use a consistent tools interface
- 03Integrate with Claude, GPT, and LangChain
- 04Run Python tools in-process
- 05Pass arguments and environment variables
Use cases
- 01Build chatbots that use custom tools
- 02Reuse tools across supported AI frameworks
- 03Run tool code locally in an environment
MCP support
The input describes an SDK for AI tools but does not state an MCP relationship.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEOpenAPITools SDK
Introduction
OpenAPITools Python package enables developers to manage, and execute tools across multiple AI API providers. It provides a unified interface for working with tools in Anthropic's Claude, OpenAI's GPT models, and LangChain frameworks.
With OpenAPITools, you can:
- Create tools as Python or Bash scripts with standardized input/output
- Access these tools through a single, consistent SDK
- Integrate tools with Claude, GPT, and LangChain models
- Build interactive chatbots that can use tools to solve complex tasks
Installation
Prerequisites
- Python 3.8 or later
- Access keys to at least one of the supported AI providers (Anthropic, OpenAI, or LangChain)
- Get an API key for OpenAPITools from the Settings page
Install from PyPI
pip install reacter-openapitools requests
If you're using the LangChain adapter, you’ll also need to install langchain and langchain-core:
pip install langchain langchain-core
Tool Execution Details
Python Tools
- Python tools are executed using Python's
exec()function directly in the current process - Benefits:
- No interpreter startup overhead
- Full privacy (code runs locally)
- Faster execution compared to subprocess methods
- Python tools receive arguments via an
input_jsondictionary and can access environment variables throughinput_json["openv"]
Bash Tools
- Bash tools are executed as subprocesses
- Arguments are passed as JSON to the script's standard input
- Recommended for non-Python environments for better performance
- Note: Bash tools should be tested in Linux environments or WSL, as they may not function correctly in Windows
Usage Modes
Local Mode (preferred)
adapter = ToolsAdapter(folder_path="/path/to/tools")
API Mode (rate limits apply)
adapter = ToolsAdapter(api_key="your_api_key")
Performance Considerations
- Python Tools: Best for Python environments, executed in-process with minimal overhead
- Bash Tools: Better for non-Python servers or when isolation is needed
- For maximum performance in non-Python environments, prefer Bash tools
Security and Privacy
- All tool execution happens locally within your environment
- No code is sent to external servers for execution
- Environment variables can be securely passed to tools
Integration with AI Models
OpenAPITools provides native integration with:
- Anthropic's Claude
- OpenAI's GPT models
- LangChain frameworks
This allows you to build AI assistants that can leverage tools to perform complex tasks.
Visit docs.openapitools.com for more information on how to use the OpenAPITools SDK, including detailed examples and API references.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.