About Traa Mcp
TRAA MCP Server lets MCP clients inspect available displays and windows and capture their contents. It supports stdio and SSE, with options to create or save screenshots in configurable sizes and JPEG or PNG formats.
Key features
- 01Enumerate displays and windows
- 02Capture a display or window
- 03Set screenshot dimensions
- 04Create or save snapshots
- 05Support JPEG and PNG output
- 06Offer stdio and SSE transports
Use cases
- 01List available screen and window sources
- 02Capture a chosen display or window
- 03Save screenshots to a specified file path
MCP support
The server exposes source enumeration and screenshot creation and saving tools to MCP clients over stdio or SSE.
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 READMETRAA MCP Server
TRAA MCP Server is a screen capture server based on the Model Context Protocol (MCP). It provides functionality for enumerating system screens and windows, as well as capturing screenshots. The server communicates with clients through the MCP protocol, supporting both standard input/output (stdio) and Server-Sent Events (SSE) transport methods.
Features
-
Screen and Window Source Enumeration
- List all available displays in the system
- List all available windows in the system
- Each source includes ID, title, type (display/window), and position information
-
Screen Capture
- Capture screenshots of any display or window
- Customizable screenshot dimensions
- Support for both JPEG and PNG formats
- Configurable image quality settings
- Automatic directory creation for saving files
Tools
-
enum_screen_sources- Enumerate all screen and window sources available on the system and return a list of SimpleScreenSourceInfo
- Returns: list[SimpleScreenSourceInfo]
-
create_snapshot- Create a snapshot of the screen source with the given ID and return it as an image
- Inputs:
- source_id: int
- snapshot_size: tuple[int, int]
- Returns: Image
-
save_snapshot- Save a snapshot of the screen source with the given ID to a file
- Inputs:
- source_id: int
- snapshot_size: tuple[int, int]
- file_path: str
- Returns: None
Example

Usage
Configure MCP Servers
Claude Desktop or other AI agents
{
"mcpServers": {
"traa_mcp": {
"command": "absolute/path/to/uv",
"args": [
"--directory",
"absolute/path/to/traa-mcp",
"run",
"traa_mcp_server"
]
}
}
}
Server Side
The server supports two running modes:
- stdio mode (default):
uv run traa_mcp_server
- SSE mode (with port specification):
uv run traa_mcp_server-sse --port 3001(default)
Client Side
The client provides an interactive command-line interface for easy access to server functionality:
uv run traa_mcp_client
After starting, the client displays a list of all available tools. You can:
- Use
enum_screen_sourcesto view all available screen and window sources - Use
create_snapshotto capture screenshots and get image data - Use
save_snapshotto save screenshots directly to files
Image Format Support
-
JPEG Format
- Best for screenshots with many colors
- Smaller file size
- Quality setting available (1-100)
- Automatically converts to RGB color space
-
PNG Format
- Best for screenshots with text or sharp edges
- Lossless compression
- Supports transparency (RGBA)
- Larger file size but better quality
Dependencies
- Python >= 3.10
- mcp >= 1.0.0
- anyio >= 4.5
- traa >= 0.1.5
- pillow >= 11.1.0 (for image processing)
Notes
- For MCP model compatibility, JPEG format with quality=60 is used by default to keep file sizes under 1MB
- When saving files, parent directories are automatically created if they don't exist
- Error handling includes detailed messages for easier troubleshooting
License
See the LICENSE file for details.
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.