How to Use the BugBug MCP in AutoGen

Q: How do AutoGen agents share BugBug tool outputs?

When an agent calls runtest, the execution ID is shared in the group chat context. Other agents can then use gettestrun to monitor the execution and discuss the results.

Q: Can an AutoGen agent decide to stop a failing BugBug suite?

Yes. A monitoring agent can check getsuiterun and, if it detects critical failures, instruct the group to halt the release pipeline.

Let your AutoGen agents run and evaluate BugBug browser tests through collaborative debate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BugBug MCP to AutoGen

Create your Vinkius account to connect BugBug to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup BugBug with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute QA workflows with this MCP Server

Let your specialized agents coordinate browser testing. A developer agent can write code, and a QA agent can immediately run `run_test` to verify the build. If the test fails, the QA agent passes the failure details from `get_test_run` back to the developer agent to fix the code, repeating until they achieve a clean run.

Analyze test suites in AutoGen conversations

Set up a debate between a performance agent and a release manager. This MCP connection lets a performance agent use `list_suite_runs` to flag slow test suites that block deployments. They use `get_suite` to analyze the suite configuration and negotiate whether to split up the tests or run them in parallel to save time.

Explore QA projects collaboratively

Let your planning agents map out your test coverage. An agent calls `list_projects` to identify the active web applications requiring validation. It then uses `list_tests` to check if key user journeys are covered, flagging missing test cases to your engineering agent for creation.

Setup guide

Set up BugBug 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 BugBug 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="BugBug_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent BugBug 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="BugBug_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent BugBug 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 BugBug. 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 BugBug 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 BugBug MCP in AutoGen

When an agent calls `run_test`, the execution ID is shared in the group chat context. Other agents can then use `get_test_run` to monitor the execution and discuss the results.

Yes. A monitoring agent can check `get_suite_run` and, if it detects critical failures, instruct the group to halt the release pipeline.

You load the tools from the MCP server using the AutoGen extension. This automatically maps the BugBug schemas to the agent's function definitions.

Yes, different agents can trigger separate tests simultaneously using the MCP interface, then coordinate their analysis of the results in a shared thread.

Yes, your BugBug API keys are securely managed by Vinkius and never exposed to the agent conversations. Only the raw test results and run statuses are visible to your agents.

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