Mcpml
What is Mcpml
MCPML (MCP Server Markup Language) is a Python framework designed for building MCP Servers with support for Command Line Interface (CLI) and OpenAI Agents.
Use cases
Use cases for MCPML include building AI-driven applications, creating custom server tools, integrating OpenAI agents into existing systems, and developing solutions that require structured data handling.
How to use
To use MCPML, install it via pip and run commands using the CLI. You can configure the server with a YAML file and execute various commands to manage tools and services.
Key features
Key features include a robust MCP Server Framework, CLI tools for server management, OpenAI Agent SDK support, agent-to-MCP integration, an extensible architecture for custom tools, dynamic loading of agent types, and structured output using Pydantic models.
Where to use
MCPML can be utilized in various fields such as artificial intelligence, software development, and any domain requiring the integration of agents with model context protocols.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcpml
MCPML (MCP Server Markup Language) is a Python framework designed for building MCP Servers with support for Command Line Interface (CLI) and OpenAI Agents.
Use cases
Use cases for MCPML include building AI-driven applications, creating custom server tools, integrating OpenAI agents into existing systems, and developing solutions that require structured data handling.
How to use
To use MCPML, install it via pip and run commands using the CLI. You can configure the server with a YAML file and execute various commands to manage tools and services.
Key features
Key features include a robust MCP Server Framework, CLI tools for server management, OpenAI Agent SDK support, agent-to-MCP integration, an extensible architecture for custom tools, dynamic loading of agent types, and structured output using Pydantic models.
Where to use
MCPML can be utilized in various fields such as artificial intelligence, software development, and any domain requiring the integration of agents with model context protocols.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
MCP Server Markup Language (MCPML)
A Python framework for building Model Context Protocol (MCP) servers with CLI and OpenAI Agent support.
Features
- 🚀 MCP Server Framework: Build MCP-compliant servers in Python
- 🔧 CLI Tools: All server capabilities exposed as CLI commands (to be consumed by humans or scripts rather than MCP clients)
- 🤖 OpenAI Agent SDK Support: Implement tools as OpenAI agents Or as simple python functions
- 🔄 Agent-to-MCP Integration: Agents can consume MCP services via config
- 🛠️ Extensible Architecture: Easily add custom tools and services
- 🔌 Dynamic Loading: Support for custom agent types and tool implementations from the execution directory
- 📦 Structured Output: Support for structured output using Pydantic models
Installation
pip install git+https://github.com/a5c-ai/mcpml#egg=mcpml
.env
OPENAI_API_KEY=your_openai_api_key
or
AZURE_OPENAI_ENDPOINT=https://your-azure-openai-endpoint.openai.azure.com AZURE_OPENAI_API_KEY=your_azure_openai_api_key OPENAI_API_VERSION=api_version
Usage
mcpml --help
mcpml run
mcpml.yaml is the default config file for the MCPML server.
mcpml run -c https://github.com/a5c-ai/some-mcpml-server
mcpml -c mcpml.yaml tools some-tool run --arg1 value1 --arg2 value2
using uvx:
uvx --from git+https://github.com/a5c-ai/mcpml#egg=mcpml mcpml -c mcpml.yaml tools list uvx --from git+https://github.com/a5c-ai/mcpml#egg=mcpml mcpmp run --transport=sse
License
MIT
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
