How to Use the BugBug MCP in CrewAI

Q: How do specialized CrewAI agents share BugBug test results?

The monitoring agent calls gettestrun and writes the output to the crew's shared memory. The debugging agent then reads this data to analyze the failure.

Q: What is the best way to restrict CrewAI agents to specific BugBug suites?

You can use the MCP Server HTTP transport with a toolfilter to only expose listsuites and runsuite, preventing agents from modifying projects or running unauthorized tests.

Q: Can CrewAI agents compare current and past runs?

Yes, an agent can call listtestruns to pull history, then use gettestrun on specific IDs to compare execution times and spot performance degradation.

Q: How does CrewAI protect my test suite configurations?

Your credentials and test suite definitions accessed via getsuite are managed within the Vinkius sandbox. Only the text outputs needed for the agents' tasks are shared over the secure transport.

Deploy a team of specialized CrewAI agents to run BugBug browser tests, monitor runs, and diagnose regressions autonomously.

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 CrewAI

Create your Vinkius account to connect BugBug to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run BugBug test suites with specialized CrewAI agents

Stop relying on single scripts to manage your browser testing. With this MCP Server, you can assign a QA Monitor agent to trigger `run_suite` while a separate Debugger agent stands by. The Monitor agent tracks execution progress using `get_suite_run` and shares the results in common memory. If a suite fails, the Debugger agent takes over. It uses `get_test` and `list_test_runs` to analyze previous runs, determining if the failure is a new regression or a known flaky test before reporting back.

Let CrewAI monitor BugBug test runs autonomously

Keep your staging environments clean without manual oversight. A CrewAI agent can run on a schedule, calling `list_suite_runs` to check the health of your deployments. It flags any anomalous failures and correlates them with recent git commits. When the agent spots a broken run, it uses `get_suite` to extract the failing steps. It then writes a detailed bug report, complete with the failing selector and the execution history, saving your team hours of triage.

Manage runner access using the BugBug MCP Server

Staging environments are often locked down, blocking external browser tests. Your CrewAI infrastructure agent can run `get_ips` to identify the active BugBug test runner addresses. It then coordinates with your DevOps tools to open the necessary ports. Once the tests finish, the agent cleans up after itself. It removes the temporary IPs from your firewall, ensuring your staging environment remains closed to the public internet while keeping browser tests functional.

Setup guide

Set up BugBug MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke BugBug tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="BugBug Analyst",
    goal="Access and analyze BugBug data via MCP.",
    backstory="Expert analyst with direct BugBug access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent BugBug transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="BugBug Analyst",
        goal="Access and analyze BugBug data via MCP.",
        backstory="Expert analyst with direct BugBug access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent BugBug transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Yes, you can set up a CrewAI agent that listens to alerts, triggers `run_test` via the MCP Server, and reports the status back to the channel.

The monitoring agent calls `get_test_run` and writes the output to the crew's shared memory. The debugging agent then reads this data to analyze the failure.

You can use the MCP Server HTTP transport with a `tool_filter` to only expose `list_suites` and `run_suite`, preventing agents from modifying projects or running unauthorized tests.

Yes, an agent can call `list_test_runs` to pull history, then use `get_test_run` on specific IDs to compare execution times and spot performance degradation.

Your credentials and test suite definitions accessed via `get_suite` are managed within the Vinkius sandbox. Only the text outputs needed for the agents' tasks are shared over the secure transport.

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