MCPML
by a5c-ai
MCPML is a Python framework for building Model Context Protocol (MCP) servers with CLI and OpenAI Agent support. It allows you to create MCP-compliant servers and integrate them with OpenAI agents.
Last updated: N/A
What is MCPML?
MCPML is a Python framework designed to simplify the creation of Model Context Protocol (MCP) servers. It provides tools and structure for building servers that can interact with MCP clients and OpenAI agents.
How to use MCPML?
To use MCPML, first install it using pip. Configure your OpenAI API key or Azure OpenAI credentials in a .env file. Then, use the mcpml command-line tool to run the server, execute tools, and manage configurations. You can run the server with mcpml run using a mcpml.yaml config file or specify a config file using the -c option. You can also use uvx to run MCPML from the git repository.
Key features of MCPML
MCP Server Framework
CLI Tools
OpenAI Agent SDK Support
Agent-to-MCP Integration
Extensible Architecture
Dynamic Loading
Structured Output
Use cases of MCPML
Building MCP-compliant servers
Integrating AI agents with MCP services
Creating custom tools and services for MCP
Exposing server capabilities through CLI commands
Managing and configuring MCP servers
Enabling structured output from MCP services
FAQ from MCPML
What is Model Context Protocol (MCP)?
What is Model Context Protocol (MCP)?
MCP is a protocol for managing and sharing context between different models and services.
How do I install MCPML?
How do I install MCPML?
Use pip install git+https://github.com/a5c-ai/mcpml#egg=mcpml
How do I configure my OpenAI API key?
How do I configure my OpenAI API key?
Set the OPENAI_API_KEY environment variable in a .env file.
What is the default configuration file?
What is the default configuration file?
The default configuration file is mcpml.yaml.
Can I use Azure OpenAI?
Can I use Azure OpenAI?
Yes, you can configure AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_API_KEY, and OPENAI_API_VERSION in your .env file.