What are the runtime dependencies of Traa Mcp?
Python 3.10 or later, along with packages `mcp >= 1.0.0`, `anyio >= 4.5`, `traa >= 0.1.5`, and `pillow >= 11.1.0`.
@opentraa
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"traa-mcp": {
"command": "uv",
"args": [
"run",
"traa_mcp_server"
]
}
}
}list[SimpleScreenSourceInfo]
source_id: int
Image
source_id: int
None
Traa Mcp is a screen capture server based on the Model Context Protocol (MCP). It enumerates system screens and windows and captures screenshots, communicating with clients via stdio or SSE transport. It is designed for use with MCP-compatible AI agents like Claude Desktop.
Configure the server in your MCP client (e.g., Claude Desktop) by adding a JSON entry with the uv command pointing to the traa_mcp_server module. Alternatively, run the server directly in stdio mode (uv run traa_mcp_server) or SSE mode with a specific port (uv run traa_mcp_server-sse --port 3001). A client-side CLI is also available (uv run traa_mcp_client) for interactive tool access.
Python 3.10 or later, along with packages `mcp >= 1.0.0`, `anyio >= 4.5`, `traa >= 0.1.5`, and `pillow >= 11.1.0`.
It supports both standard input/output (stdio) and Server-Sent Events (SSE) transport.
JPEG and PNG. JPEG is best for colorful content with smaller file sizes; PNG is lossless and supports transparency.
JPEG quality is set to 60 by default to keep file sizes under 1 MB for MCP model compatibility.
Yes, it enumerates and captures both display screens and application windows.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Open-source MCP to use Blender with any LLM

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Comments