Percy MCP Server for AutoGen 10 tools — connect in under 2 minutes
Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add Percy as an MCP tool provider through Vinkius and every agent in the group can access live data and take action.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with McpWorkbench(
server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
transport="streamable_http",
) as workbench:
tools = await workbench.list_tools()
agent = AssistantAgent(
name="percy_agent",
tools=tools,
system_message=(
"You help users with Percy. "
"10 tools available."
),
)
print(f"Agent ready with {len(tools)} tools")
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Percy MCP Server
Inject precision quality assurance workflows directly bounding LLM models via the Percy Visual Testing API (by BrowserStack). Programmatically verify pixel regressions executing queries evaluating visual boundaries natively across target projects. Inspect deep status arrays parsing CI build limits dynamically, extract metrics evaluating granular snapshot checkpoints asynchronously, and force immediate test baseline approvals seamlessly directly from explicit prompt commands naturally.
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Percy tools. Connect 10 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
What you can do
- Project Navigation — Read bounded parameters tracking Percy deployments isolating configurations determining explicitly specific active QA targets natively
- Automated Build Oversight — Track specific arrays extracting dynamic checks returning pipeline checkpoints (approved/failed/unreviewed limits) explicitly seamlessly
- Visual Snapshot Operations — Log natively extracting bounds verifying comparison properties logging rendering differences mapping exact explicit width constraints
- Baseline Affirmations — Mutate bounding loops forcing active execution of JSON logic structurally bypassing native clicks allowing test approvals implicitly (
approve_buildorapprove_snapshot)
The Percy MCP Server exposes 10 tools through the Vinkius. Connect it to AutoGen in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Percy to AutoGen via MCP
Follow these steps to integrate the Percy MCP Server with AutoGen.
Install AutoGen
Run pip install "autogen-ext[mcp]"
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Integrate into workflow
Use the agent in your AutoGen multi-agent orchestration
Explore tools
The workbench discovers 10 tools from Percy automatically
Why Use AutoGen with the Percy MCP Server
AutoGen provides unique advantages when paired with Percy through the Model Context Protocol.
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Percy tools to solve complex tasks
Role-based architecture lets you assign Percy tool access to specific agents. a data analyst queries while a reviewer validates
Human-in-the-loop support: agents can pause for human approval before executing sensitive Percy tool calls
Code execution sandbox: AutoGen agents can write and run code that processes Percy tool responses in an isolated environment
Percy + AutoGen Use Cases
Practical scenarios where AutoGen combined with the Percy MCP Server delivers measurable value.
Collaborative analysis: one agent queries Percy while another validates results and a third generates the final report
Automated review pipelines: a researcher agent fetches data from Percy, a critic agent evaluates quality, and a writer produces the output
Interactive planning: agents negotiate task allocation using Percy data to make informed decisions about resource distribution
Code generation with live data: an AutoGen coder agent writes scripts that process Percy responses in a sandboxed execution environment
Percy MCP Tools for AutoGen (10)
These 10 tools become available when you connect Percy to AutoGen via MCP:
approve_build
/approve` moving the test suite to green. Approve all unreviewed snapshots in a Percy build. Marks the entire build as visually approved for deployment
approve_snapshot
Approve a single Percy snapshot. Marks it as visually correct, updating the baseline for future comparisons
get_build_details
Get full details of a Percy build including state, total/unreviewed snapshot counts, approved/rejected snapshots, branch, commit SHA, and finalized timestamp
get_project_details
Get full details of a Percy project including name, slug, default branch, auto-approve enabled, browser targets, and build count
get_snapshot_details
Get full details of a Percy snapshot including name, review state, widths, fingerprint, and comparison count
list_browsers
List all supported browser families on Percy. Returns browser names, versions, and OS combinations for cross-browser visual testing
list_builds
List builds for a Percy project. Each build contains snapshots from a test run. Returns build IDs, states (processing/finished/failed), branch names, commit SHAs, and snapshot counts
list_comparisons
List visual comparisons for a Percy snapshot. Each comparison shows the diff between baseline and head at a specific width/browser. Returns diff images, diff percentages, and browser info
list_projects
List all projects on Percy (BrowserStack). Percy is the leading visual regression testing platform that captures snapshots and detects pixel-level UI differences across builds. Uses JSON:API format. Returns project names, slugs, and browser configs
list_snapshots
List snapshots in a Percy build. Each snapshot is a captured page/component at specific widths and browsers. Returns snapshot names, review states (unreviewed/approved/rejected), and diff percentages
Example Prompts for Percy in AutoGen
Ready-to-use prompts you can give your AutoGen agent to start working with Percy immediately.
"Log explicitly the builds targeting structural limits seamlessly isolating project 'org-slug/my-app' dynamically checking bounding states natively."
"Reverse check explicit structures extracting limits comparing properties cleanly bounding snapshot ID 'snap_778' natively efficiently."
"Force explicit validation mutating boundaries executing structurally an approval across build ID '8910' automatically natively flawlessly securely."
Troubleshooting Percy MCP Server with AutoGen
Common issues when connecting Percy to AutoGen through the Vinkius, and how to resolve them.
McpWorkbench not found
pip install "autogen-ext[mcp]"Percy + AutoGen FAQ
Common questions about integrating Percy MCP Server with AutoGen.
How does AutoGen connect to MCP servers?
Can different agents have different MCP tool access?
Does AutoGen support human approval for tool calls?
Connect Percy with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Percy to AutoGen
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.