How to Use the Percy MCP in Pydantic AI

Q: How do I configure the Percy toolset in Pydantic AI?

Instantiate MCPToolset with your HTTP server URL and pass it to your Agent constructor via the toolsets parameter to access tools like listprojects.

Q: Does this integration support the deprecated MCPServerHTTP class?

No. You must use the unified MCPToolset class to connect your external server, ensuring compatibility with the latest package versions.

Run type-safe visual regression checks and approve Percy builds with strict Pydantic AI runtime validation.

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 Pydantic AI

Create your Vinkius account to connect Percy to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate visual test states with Pydantic AI

This MCP Server exposes Percy's visual testing API as strictly typed tools. Every response from tools like `get_build_details` or `list_snapshots` is parsed and validated against concrete schemas before your agent processes them. By registering the `MCPToolset` in your type-safe agent, you guarantee that API changes never corrupt your deployment logic. No silent corruption. No guessing games. If a payload from `list_builds` contains unexpected fields, the agent fails loudly instead of executing bad code.

Execute type-safe baseline approvals

Handling baseline updates and layout comparisons becomes completely bulletproof. The server allows your agent to safely update design baselines using `approve_snapshot` and `approve_build` which require precise string parameters validated at runtime. When managing complex visual updates, the agent uses `list_comparisons` to verify the exact layout drift. The strict schema validation ensures your agent only approves builds that match your exact visual regression thresholds.

Inspect project metadata with type safety

Retrieving project and browser configurations for validation is direct. It exposes deep project and browser configurations through `get_project_details` and `list_browsers`. You configure this integration by instantiating the MCP Server toolset with your external server URL and adding it to the agent's `toolsets` list. This setup ensures your visual validation pipelines remain completely type-safe from end to end.

Setup guide

Set up Percy MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "percy-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Percy tools.",
)

result = await agent.run("List recent Percy transactions")
print(result.output)

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 Pydantic AI

Instantiate `MCPToolset` with your HTTP server URL and pass it to your `Agent` constructor via the `toolsets` parameter to access tools like `list_projects`.

The agent raises a strict validation error immediately, preventing the execution of downstream tools like `approve_build` on malformed data.

Yes. Because the framework is model-agnostic, you can route validated outputs from `get_snapshot_details` to local models or commercial APIs.

No. You must use the unified `MCPToolset` class to connect your external server, ensuring compatibility with the latest package versions.

Your API tokens and project configurations are isolated in ephemeral V8 sandboxes, meaning your layout structures and project metadata are never cached or exposed to the model.

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