Related Servers

No user-submitted related servers found.

Related Servers

• Desktop-MCP

  talkwitharnav-web

  A

  license

  -Not graded

  quality

  B

  maintenance

  Enables supervised, visible control of a Windows desktop from an MCP client, providing real mouse and keyboard input, screenshots, local safety controls, and a teaching mode for guidance without injection.

  Updated a month ago (2026-09-12 21:38 UTC)

  MIT

• AInotate

  dontpayfull

  A

  license

  A

  quality

  A

  maintenance

  Enables MCP clients to capture web pages, windows or screenshots and annotate them with numbered steps, boxes, arrows, labels, magnifiers, keycaps and solid redaction, returning JSON results plus a small preview image so the model can verify its work before sharing.

  Updated 18 hours ago (2026-10-20 20:55 UTC)

  10

  16

  402 PyPI

  6

  AGPL 3.0

• Screen Agent

  chriswu727

  A

  license

  -Not graded

  quality

  C

  maintenance

  Enables AI assistants to capture screenshots and control desktop input (mouse, keyboard) to see and interact with your screen. Features user-first safety controls including automatic pause on user activity and app allowlists to restrict interactions to approved applications only.

  Updated 2 days ago (2026-10-19 17:11 UTC)

  1

  MIT

• AgentViewport

  guybnd

  A

  license

  -Not graded

  quality

  D

  maintenance

  Enables AI agents to view and control the local desktop through browser-based viewport and MCP tools.

  Updated 9 months ago (2026-01-29 16:36 UTC)

  MIT

• assistant-vision

  nascom-fiduciaire

  A

  license

  -Not graded

  quality

  C

  maintenance

  Enables an assistant to visually monitor a selected desktop window through screenshots and perform mouse and keyboard actions, with visual feedback for each step.

  Updated a month ago (2026-09-08 09:18 UTC)

  MIT

• lookhere

  yskim3271

  A

  license

  -Not graded

  quality

  B

  maintenance

  Enables users to capture any screen or URL, box the region they mean, attach notes, and deliver that annotated feedback—including cropped images, numbered boxes, and the underlying DOM elements or component names—directly to an AI coding agent over MCP. It also lets agents open the annotator, capture a URL, and wait for or retrieve feedback bundles from earlier sessions.

  Updated 19 days ago (2026-10-02 12:45 UTC)

  MIT