How to Use the Amazing Marvin MCP in CrewAI

Q: How do I add the Amazing Marvin MCP Server to my CrewAI agents?

Pass your Vinkius endpoint URL directly into the mcps array when defining your CrewAI agents. The framework automatically discovers all nine Marvin tools.

Q: Can multiple CrewAI agents use Amazing Marvin MCP tools at the same time?

Yes, your crew can run tools like gettodayitems and updatetask in parallel. Vinkius handles the concurrent requests safely in isolated runtimes.

Q: How does CrewAI handle task hierarchy in Amazing Marvin?

Your supervisor agent can call getchildren to inspect your workspace layout, then direct other agents to add tasks to specific folders.

Q: Can I restrict which Amazing Marvin MCP tools my CrewAI team can use?

Yes, you can use the MCPServerHTTP class from crewai.mcp with a tool filter to expose only specific tools like markdone to your agents.

Let your CrewAI agent teams coordinate, schedule, and track tasks directly inside Amazing Marvin.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazing Marvin MCP to CrewAI

Create your Vinkius account to connect Amazing Marvin 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 Amazing Marvin with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Scheduling with CrewAI

The `add_task` tool lets your specialized crew members assign work to your calendar based on their research. For example, a planner agent analyzes your inbox and calls this tool to schedule your day. By using this MCP Server on Vinkius, your entire CrewAI team shares access to the same Marvin database. They pass parent category IDs to keep your workspace organized without human intervention.

Coordinated Project Building

The `add_project` tool allows your supervisor agent to build high-level folders before assigning specific sub-tasks. The agent creates the project container, then passes the ID to worker agents. The worker agents then use `add_category` or `add_task` to populate the new project. This hierarchical execution ensures your team doesn't dump raw tasks into your root folder.

Autonomous Time Management

The `start_tracking` tool enables your execution agents to log their active work sessions as they process your queue. A monitoring agent watches the session and triggers `stop_tracking` when the job finishes. This autonomous loop keeps your Marvin timesheets accurate. Your crew runs these MCP tools over secure HTTP transports managed by Vinkius, ensuring reliable execution.

Setup guide

Set up Amazing Marvin 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 Amazing Marvin tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Amazing Marvin 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="Amazing Marvin Analyst",
        goal="Access and analyze Amazing Marvin data via MCP.",
        backstory="Expert analyst with direct Amazing Marvin access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Amazing Marvin 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 Amazing Marvin. 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 Amazing Marvin 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 Amazing Marvin MCP in CrewAI

Pass your Vinkius endpoint URL directly into the `mcps` array when defining your CrewAI agents. The framework automatically discovers all nine Marvin tools.

Yes, your crew can run tools like `get_today_items` and `update_task` in parallel. Vinkius handles the concurrent requests safely in isolated runtimes.

Your supervisor agent can call `get_children` to inspect your workspace layout, then direct other agents to add tasks to specific folders.

Yes, you can use the `MCPServerHTTP` class from `crewai.mcp` with a tool filter to expose only specific tools like `mark_done` to your agents.

Vinkius isolates every session in a zero-trust sandbox. Your tasks, projects, and time-tracking data are processed ephemerally and never stored on disk.

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