How to Use the Percy MCP in Claude

Q: How do I trigger a Percy visual check review inside Claude Desktop?

Ask Claude Desktop to run listbuilds to find your latest run. The agent will fetch the build status and let you inspect individual visual regressions directly in your chat.

Q: Can I approve individual visual snapshots using Percy with Claude Desktop?

Yes. Use the approvesnapshot tool within Claude Desktop to accept a single UI change. This updates your baseline without forcing you to approve the entire build.

Q: How does Claude Desktop handle browser target verification in Percy?

Claude Desktop calls listbrowsers to pull the active OS and browser configurations. This ensures your agent evaluates visual diffs across the exact environments you target.

Q: What is the fastest way to check project configurations?

Your agent uses the getprojectdetails MCP tool to pull the default branch and auto-approve settings. This gives you instant visibility into your visual testing setup.

Review visual diffs and approve Percy builds directly within Claude Desktop without leaving your chat window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Percy MCP to Claude Desktop

Create your Vinkius account to connect Percy to Claude Desktop — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Percy with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Inspect live visual regressions inside Claude Desktop

The `list_builds` tool pulls active test runs from your BrowserStack account straight into your Claude Desktop chat window. You get the exact build state, commit SHA, and unreviewed snapshot counts without opening a browser tab. Your agent uses `get_build_details` to isolate failing runs and identify which branch broke the UI. This lets you pinpoint visual drift during a live debugging session.

Resolve pixel-level diffs using this MCP Server

This Percy MCP Server lets Claude Desktop run `list_snapshots` to extract every captured page layout and its corresponding diff percentage. You see exactly which widths and browser targets failed your visual checks. The agent calls `list_comparisons` to fetch the specific visual diff images and target browser specs. It analyzes the pixel changes to tell you if a button shifted or a layout collapsed.

Ship UI updates by approving builds in Claude Desktop

Marking an entire test suite as visually correct is fast with the `approve_build` tool, which your agent triggers directly from the desktop interface using this MCP tool. This action updates your baseline and unblocks your deployment pipeline instantly. If you only need to fix a single component, `approve_snapshot` targets the exact visual failure. You approve the specific layout change and let the rest of the build run its course.

Setup guide

Set up Percy MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Percy MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Percy MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under percy-mcp.

json

{
  "mcpServers": {
    "percy-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Percy. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Percy now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Percy MCP in Claude Desktop

Ask Claude Desktop to run `list_builds` to find your latest run. The agent will fetch the build status and let you inspect individual visual regressions directly in your chat.

Yes. Use the `approve_snapshot` tool within Claude Desktop to accept a single UI change. This updates your baseline without forcing you to approve the entire build.

Claude Desktop calls `list_browsers` to pull the active OS and browser configurations. This ensures your agent evaluates visual diffs across the exact environments you target.

Your agent uses the `get_project_details` MCP tool to pull the default branch and auto-approve settings. This gives you instant visibility into your visual testing setup.

Vinkius runs this server in a secure, ephemeral V8 sandbox that only transmits metadata like snapshot names and diff percentages. Your actual source code and sensitive asset files never leave your local environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript