How to Use the Mabl (AI-Powered Test Automation) MCP in CrewAI

Q: How do I expose Mabl (AI-Powered Test Automation) MCP Server tools to my CrewAI agents?

Pass the server URL directly into the mcps array when defining your agent. For stricter control, use MCPServerHTTP with a toolfilter to give the Triage agent mb.getexecution while restricting triggers.

Q: Can a CrewAI agent trigger a Mabl (AI-Powered Test Automation) plan autonomously?

Yes. An agent equipped with mb.triggerplan will fire the deployment event based on its instructions. You define the conditions in the agent's prompt, and it executes the tool when those conditions are met.

Q: How do multiple CrewAI agents share Mabl (AI-Powered Test Automation) execution data?

One agent calls mb.listexecutions and writes the output to the crew's shared memory. A downstream agent reads that memory and decides if it needs to pull deeper logs via mb.getexecution.

Deploy autonomous QA teams in CrewAI to monitor, trigger, and analyze Mabl test executions without human intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mabl (AI-Powered Test Automation) MCP to CrewAI

Create your Vinkius account to connect Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous QA Teams via MCP

This MCP server turns Mabl into the primary toolkit for your CrewAI agent teams. You assign a Release Manager agent to coordinate testing, giving it access to `mb.list_plans` and `mb.trigger_plan`. It decides exactly which test suites to run based on the current deployment context. Meanwhile, a dedicated Triage agent waits for the results. It polls `mb.list_executions` to spot failures. You stop treating testing as a linear script and start treating it as a collaborative operation between specialized agents.

Deep Failure Analysis Delegation

When a test goes red, your CrewAI setup handles the investigation autonomously. The MCP integration lets the Triage agent grab the specific failure details using `mb.get_execution`, pulling the duration, test outcomes, and screenshots. It reads the AI-driven failure analysis provided by Mabl. It then passes these findings to a Developer agent in your crew. The Developer agent cross-references the failure with recent commits. The human team gets a root cause summary instead of a generic build failure notification.

Environment and Workspace Auditing

You can deploy a dedicated Audit agent to map out your testing infrastructure. By combining `mb.workspace_info` with `mb.get_app`, this agent documents exactly which web URLs and API base targets are actively under test. The agent categorizes everything using `mb.list_labels` and `mb.list_envs`. It builds a complete picture of your Mabl configuration and stores it in shared memory. Other agents in your crew query this memory to make informed decisions before triggering new runs.

Setup guide

Set up Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Mabl (AI-Powered Test Automation) 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="Mabl (AI-Powered Test Automation) Analyst",
        goal="Access and analyze Mabl (AI-Powered Test Automation) data via MCP.",
        backstory="Expert analyst with direct Mabl (AI-Powered Test Automation) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Mabl (AI-Powered Test Automation) 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 Mabl. 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 Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) MCP in CrewAI

Pass the server URL directly into the `mcps` array when defining your agent. For stricter control, use `MCPServerHTTP` with a `tool_filter` to give the Triage agent `mb.get_execution` while restricting triggers.

Yes. An agent equipped with `mb.trigger_plan` will fire the deployment event based on its instructions. You define the conditions in the agent's prompt, and it executes the tool when those conditions are met.

One agent calls `mb.list_executions` and writes the output to the crew's shared memory. A downstream agent reads that memory and decides if it needs to pull deeper logs via `mb.get_execution`.

CrewAI supports stdio, SSE, and Streamable HTTP. You configure the transport type in your MCP client setup depending on how you deploy your Python environment.

The server handles your workspace names, organization IDs, and API base URLs. We use isolated sandboxing for every connection. Once your CrewAI script terminates, the environment vanishes. Zero data is retained on our infrastructure.

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