Skip to content
botshub

SECTION WIDTH VERDICT DIFF

by jamalkamaladdin

MCP serverOther

Visit SECTION WIDTH VERDICT DIFF

Measurement for coding agents building UI: extract a contract from the reference page, check the implementation, get numbers back

About SECTION WIDTH VERDICT DIFF

pixelpact measures a UI implementation against a reference page so coding agents can check their own work. The README frames the problem as an agent being unable to see the page it just built. It extracts a contract of computed styles, geometry, states, tokens and keyframes from a reference URL or Figma frame, then reports each property that differs. It is by Jamal Kamaladdin.

Besides a CLI with extract, check, diff and side-by-side commands, the README describes an MCP server exposing tools to extract a contract, check an implementation, diff pixels and read a contract summary, plus a programmatic API and a GitHub Action that comments on pull requests. It needs Node.js 22.12 or newer and Playwright with Chromium. A Figma token is optional for reading Figma frames. The README says it is framework-agnostic because it measures the rendered DOM, and the author notes the contract format will still change before 1.0. The licence is MIT. Details come from the project's README.

Key features

  • Extract a style contract from a reference
  • Check implementation deviations
  • Pixel diff
  • MCP server and CLI
  • GitHub Action

More other MCP servers

  • Mcp Proxy

    sparfenyuk

    Other

    A bridge between Streamable HTTP and stdio MCP transports

    2.8K GitHub starsPythonMIT
  • Mcp Remote

    punkpeye

    Other

    Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server.

    1.7K GitHub starsTypeScriptMIT
  • Kanzo

    emanuele-em

    Other

    Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply, starts in 2 ms, zero setup.

    1.2K GitHub starsRustAGPL-3.0
  • Other

    į”Ÿæˆå’ŒįūŽåŒ–åŊįž–čū‘åŽŸį”Ÿ PPT įš„ Agent Skill

    484 GitHub starsPythonMIT
  • mcptoon

    activeing123

    Other

    MCP tool discovery burns 71,929 tokens. mcptoon drops it to 581 (−99.2%, measured). Zero dependencies.

    431 GitHub starsPythonApache-2.0
  • automcp

    NapthaAI

    Other

    Easily convert tool, agents and orchestrators from existing agent frameworks to MCP servers

    303 GitHub starsPythonApache-2.0
Suggest an improvement
Report this listing
Is this your project? Claim this listing