How to Use the Percy MCP in AutoGen

Q: How do AutoGen agents debate visual changes in Percy?

One agent calls listsnapshots to gather visual diff percentages. It presents this data to a coordinator agent, which decides whether to proceed or request manual human review.

Q: How do I register the Percy MCP Server with AutoGen?

You use StreamableHttpServerParams to point to the server URL. The McpToolAdapter then converts the visual regression tools into schemas that your AssistantAgent understands.

Q: Can the agents handle multiple projects using this setup?

Yes, the agents call listprojects to discover active repositories. They then route their visual validation checks to the correct project slug dynamically.

Run multi-agent QA debates in AutoGen to verify and approve Percy visual builds.

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 AutoGen

Create your Vinkius account to connect Percy to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-agent visual regression debates in AutoGen

This Percy MCP Server inserts visual verification capabilities into your AutoGen agent conversations. An AutoGen developer agent can propose a build release, while an AutoGen QA agent runs `get_build_details` to verify if any Percy visual regressions occurred. The AutoGen agents debate whether the Percy visual changes are intentional. By inspecting `list_snapshots` and `list_comparisons`, the AutoGen QA agent provides pixel-level evidence to the group, preventing buggy layouts from reaching production.

Coordinate visual approvals with AutoGen

The MCP Server enables consensus-driven deployment gates using `approve_build` and `approve_snapshot`. Once the AutoGen agents agree that the Percy visual differences are acceptable, they execute the Percy approval tools. The AutoGen coordinator agent calls `get_project_details` to verify that the default Percy branch settings match the target. It then signals the AutoGen release agent to deploy, creating a completely automated, multi-agent sign-off workflow.

Multi-browser verification via AutoGen agents

Using `list_browsers` and `list_projects`, your AutoGen agents analyze cross-browser visual consistency in Percy. The AutoGen performance agent might push for fewer browser targets to save costs, while the AutoGen QA agent defends coverage. They query `get_snapshot_details` to evaluate if Percy layout bugs only happen on specific viewport widths. This collaborative AutoGen analysis ensures that your Percy visual testing resources are allocated efficiently across all active projects.

Setup guide

Set up Percy MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Percy tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Percy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Percy data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Percy_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Percy data")
    print(result.messages[-1].content)

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 AutoGen

One agent calls `list_snapshots` to gather visual diff percentages. It presents this data to a coordinator agent, which decides whether to proceed or request manual human review.

Yes, once the agents reach consensus on the visual diffs, the designated QA agent calls `approve_build` to mark the run green.

You use `StreamableHttpServerParams` to point to the server URL. The `McpToolAdapter` then converts the visual regression tools into schemas that your AssistantAgent understands.

Yes, the agents call `list_projects` to discover active repositories. They then route their visual validation checks to the correct project slug dynamically.

The server only accesses visual snapshots, project metadata, and browser configuration profiles. All visual diff calculations and comparisons are processed securely within the sandboxed 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