Skip to main content
Glama
wangkang1133

desktop-touch-mcp

by wangkang1133
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to desktop-touch-mcp

  • Glasswarp by glasswarp

    Glasswarpofficial

    glasswarp
    A
    license
    A
    quality
    B
    maintenance
    Allow AI agents to see and control a real Windows PC you own: observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH — your machine, your key.
    16
    Apache 2.0

Related Servers

  • computer-mcp

    Tb3bhargav
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP-capable AI agents to control Windows desktops through UI Automation element trees, native screenshots, app launching, batched action sequences, smart waits, and safety gates using normalized coordinates.
    MIT

  • Computer-Controller-Bridg

    Dobona
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI clients on Windows to control the local mouse, keyboard, and screen understanding via MCP stdio, allowing automated workflows like viewing the screen, locating elements, clicking, typing, and verifying results.
    1
    Apache 2.0

  • AgentDeskLink

    Takayuki-Ishimaru
    A
    license
    B
    quality
    B
    maintenance
    Enables AI agents to observe and control local browsers and desktop applications over MCP, including reading UI elements and differences, capturing images, and performing permitted clicks, typing, selections, scrolling, and multi-window operations.
    16
    2
    MIT

  • OmniFlow

    huppugo1
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI clients to automate Windows desktop applications through window manipulation, image recognition, OCR, keyboard/mouse simulation, and memory operations via the MCP protocol.
    MIT

  • AiPC

    ForeverToAI
    A
    license
    Not graded
    quality
    A
    maintenance
    Gives AI agents full control of a Windows computer over MCP through 63 native tools — screenshots and UI trees for vision, mouse/keyboard input, Chrome control via CDP, plus files, terminal, processes, and SSH/SFTP. The agent can look at the screen, click, type, launch apps, run commands, and verify each step with a fresh screenshot.
    48
    MIT
Deploy Server
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

TDQS

A3.8/5.0

Scored across 30 tools

Disambiguation3/5

Multiple clusters overlap in function: three click tools (browser_click, click_element, mouse_click), four browser-discovery tools (overview/search/locate/form), and two shell tools (shell_session, terminal). The descriptions' consistent 'Prefer X over Y' guidance resolves most ambiguity, but an agent must track CDP-vs-UIA-vs-coordinates distinctions across several near-synonym tools.

Naming Consistency3/5

The browser_* prefix (9 tools) plus mouse_*, workspace_*, and screenshot_* clusters are highly consistent, but the remaining tools mix conventions: verb_noun (click_element, focus_window, run_macro), noun_verb (window_dock, notification_show), and bare nouns (keyboard, scroll, excel). All lowercase snake_case keeps it readable, but action placement is unpredictable across the set.

Tool Count2/5

At 30 tools this exceeds the 25+ threshold and creates a heavy context and selection burden for agents. Several tools are peripheral or mergeable (screenshot_query/screenshot_gc are both cache management, server_status is diagnostics, notification_show is a one-shot utility), though the genuinely broad desktop-automation scope softens the excess somewhat.

Completeness2/5

The browser lifecycle is well covered (open, navigate, click, fill, observe, wait), but the native-desktop workflow has dead ends: desktop_discover and desktop_act are referenced as required precursors in multiple descriptions yet are absent from the tool set, so agents following documented guidance will hit tool-not-found errors. Missing browser_close/tab management and first-class element enumeration are notable gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources