Vinkius
Percy logo
Vinkius
Vinkius runs on Vercel AI SDK

How to Use the Percy MCP in Vercel AI SDK

Let your Vercel AI SDK app stream visual test results from the Percy MCP Server directly to your users in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Percy MCP on Cursor AI Code Editor MCP Client Percy MCP on Claude Desktop App MCP Integration Percy MCP on OpenAI Agents SDK MCP Compatible Percy MCP on Visual Studio Code MCP Extension Client Percy MCP on GitHub Copilot AI Agent MCP Integration Percy MCP on Google Gemini AI MCP Integration Percy MCP on Lovable AI Development MCP Client Percy MCP on Mistral AI Agents MCP Compatible Percy MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on Vercel AI SDK

Connect Percy MCP to Vercel AI SDK

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

GDPR Included with Plan

Key Capabilities

Live UI diff streaming with Vercel AI SDK

The `list_snapshots` tool fetches the latest visual states from Percy so your Vercel AI SDK application can render UI diffs on the fly. Your users see snapshot names, review states, and diff percentages populate their screens instantly while the edge function executes. By feeding `get_snapshot_details` directly into streamText, you bypass slow loading states entirely. This setup makes visual regression data immediately actionable for developers viewing their deployment dashboards.

Instant visual approvals from your frontend

The `approve_snapshot` tool updates the visual baseline on Percy directly from your custom Vercel AI SDK interface using this MCP Server. When a developer reviews a changed component, your interface triggers this tool to mark the snapshot as visually correct without leaving the deploy log. You can also call `approve_build` to green-light an entire test run when all changes are intentional. This speeds up production releases by letting engineers sign off on visual updates inside their custom chat interface.

Cross-browser test tracking on the edge

The `list_browsers` tool queries all supported browser families on Percy to show you exactly where your UI is being tested. Your Vercel AI SDK app maps these browser targets against live test runs to catch cross-browser layout bugs before they hit production. Combining this with `list_comparisons` gives your edge-rendered dashboard a clear breakdown of pixel-level differences across Chrome, Firefox, and Safari. You get direct URLs to diff images and raw percentages streamed straight to the client.

Setup guide

Set up Percy MCP in Vercel AI SDK

Prerequisites

  • Node.js 18+ and a TypeScript project
  • ai + @modelcontextprotocol/sdk packages
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install dependencies

    Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).

  2. 2

    Create the Streamable HTTP transport

    Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

  3. 3

    Discover and use tools

    Call mcpClient.tools() to auto-discover all Percy tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.

  4. 4

    Works with any model provider

    Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts
import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Percy transactions",
});

console.log(text);
await mcpClient.close();

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.

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 Vercel AI SDK

Install @ai-sdk/mcp and use createMCPClient pointing to your Vinkius endpoint. Pass the client's tools directly to streamText to let your agent manage visual tests.
Yes, your agent can call approve_build inside an edge function when it detects a green deployment. This immediately marks the Percy run as approved without manual intervention.
The SDK streams the output of list_snapshots chunk by chunk as it arrives from the API. This prevents timeout issues on Vercel edge functions when processing hundreds of visual comparisons.
Your code should catch errors from get_build_details and let the agent explain the failure. Usually, this is just a missing token or a build that is still processing on the server.
Your project slugs, branch names, and commit SHAs remain completely secure inside the Vinkius V8 Isolate Sandbox. The connection is ephemeral, and Vinkius handles the authorization token securely so your raw API keys are never exposed to the LLM or the public internet.

Start using the Percy MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Percy. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.