claude-screen-mcp
Related Servers
Alternatives to claude-screen-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to read any Windows window as text with coordinates, including control names, roles, clickability, and all on-screen text positions, so even models without vision can understand and act on the desktop. It is read-only, listing windows, finding elements by name, and waiting for text to appear, without clicking, typing, or stealing focus.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to start and stop local read-only Windows 11 screen observation sessions, then inspect redacted screen state, UI trees, frames, and wait for changes, title matches, or idle periods through stdio tools.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables an assistant to visually monitor a selected desktop window through screenshots and perform mouse and keyboard actions, with visual feedback for each step.MIT
- AlicenseAqualityBmaintenanceEnables an agent to observe and operate desktop apps and browsers through an accessibility-tree-first view, with clicking, typing, scrolling, dragging and waiting tools. Screenshot handling, coordinate mapping and fail-closed safety rules (risk confirmation, deny-listed apps, stale-observation refusal) are enforced inside the server.9Apache 2.0
- FlicenseNot gradedqualityDmaintenanceProvides screen capture, OCR text extraction, and visual language model scene understanding capabilities with continuous monitoring and automatic memory storage integration.-
- FlicenseAqualityCmaintenanceEnables observation-only system inspection through MCP, exposing system identity, resources, process summary, and network summary without any mutation or command execution.4-
TDQS
Scored across 10 tools
Most tools target clearly distinct operations (full capture, region capture, OCR, text search, recording). The one area of overlap is the change-detection trio — screenshot_if_changed, get_screen_diff, and wait_for_change all key off perceptual-hash distance — but their descriptions carefully delineate behavior (image vs diagnostics vs blocking poll), so an agent can still choose correctly.
The set predominantly follows a verb_noun convention (list_displays, read_screen_text, find_text_on_screen, get_screen_diff, wait_for_change, record_screen). Minor deviations are the bare noun 'screenshot' and 'screenshot_if_changed', but overall the pattern is predictable and readable.
Ten tools is well-scoped for a screen-capture/observation server, with each tool earning its place across capture, enumeration, OCR, and change-monitoring capabilities. Nothing feels redundant or padded.
The surface covers the full observation lifecycle: display/window enumeration, full and regional capture, OCR, text search, change detection, polling, and short recording. The notable gap is window-specific capture — list_windows returns handles but no tool captures a single window, and there are no save-to-file or input/action operations, though the latter is plausibly out of scope.