Skip to main content
Glama
Sign In
mcp-screen

mcp-screen

by ashark-ai-05
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to mcp-screen

No user-submitted related servers found.

    Related Servers

    • visual-companion

      ystyle
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables coding agents to show mockups and diagrams in a browser tab for a human to review and click, then reads those clicks back to guide visual brainstorming sessions.
      -

    • Browser MCP

      counterm
      A
      license
      Not graded
      quality
      B
      maintenance
      Exposes browser tabs to any MCP client through a local broker, letting agents discover pages, take text snapshots with numbered elements, and drive them via click, type, navigate, eval, network/log inspection, and screenshots. Supports stdio, Streamable HTTP, and SSE transports so IDE and CLI agents can orchestrate browser automation.
      MIT
    • orchords-web-pilot

      orchords-web-pilotofficial

      ORCHORDS
      F
      license
      A
      quality
      C
      maintenance
      Enables coding agents to drive a real Playwright-backed browser session, navigating, observing, interacting, and capturing proof on web pages via MCP tools across stdio and Streamable HTTP transports.
      15
      2
      -

    • Unterm

      zhitongblog
      F
      license
      Not graded
      quality
      A
      maintenance
      The terminal AI agents can drive: a cross-platform desktop terminal (macOS/Linux/Windows, MIT) that runs a local MCP server. Spawn tabs/panes, run commands with structured output, read screens and full scrollback, take scrolling screenshots, record sessions with secret redaction, switch identity profiles. Auto-registers with Claude Code / Codex / Gemini CLI on install.
      15
      -
    Deploy Server
    Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

    TDQS

    A4/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: place/update/read/remove widgets, read/clear the canvas, ask the user, and post reports. There is no overlapping functionality; the only potential confusion is between read_widget and read_canvas, but they operate at different scopes (single widget vs. entire canvas).

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (place_widget, update_widget, read_widget, read_canvas, remove_widget, clear_canvas, ask_user, post_report). No deviations or mixed conventions.

    Tool Count5/5

    With 8 tools, the set is well-scoped for a canvas UI management server. Each tool earns its place, covering creation, updates, reads, removals, bulk clearing, user interaction, and reporting without redundancy.

    Completeness5/5

    The surface provides full CRUD for widgets (create, read, update, delete, list), bulk clear, plus user interaction and reporting. No obvious gaps for the stated purpose; minor operations like reordering or renaming titles are not essential and can be inferred as part of widget data or skipped.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources