Release history
RobSpectre/mvf1 releases
MCP server that controls MultiViewer, an app for watching motorsports like Formula 1, World Endurance Championship, IndyCar and others.
All releases
2 shown
2.0.0
Breaking risk
Breaking changes
- Removed support for Python versions less than 3.10 due to dependency fastmcp
Notable features
- Added Model Context Protocol (MCP) server via `mvf1-cli mcp` for AI agent control of MultiViewer
Full changelog
MCP Server
New to this release is a Model Context Protocol (MCP) server for MultiViewer enabling AI agents to control your setup.
To launch the MCP server, simply mvf1-cli mcp.
To add to an agentic framework like PydanticAI, use their affordance for a stdio MCP server. For example:
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStdio
server = MCPServerStdio(
'mvf1-cli',
args=[
'mcp'
]
)
agent = Agent('openai:gpt-4o', mcp_servers=[server])
BREAKING CHANGE
The breaking change for this release is dropping support for Python versions <3.10, as a result of the new dependency fastmcp.