How to Use the Fellow MCP in CrewAI

Q: Can CrewAI agents update meeting notes in Fellow?

CrewAI agents can read notes using getnote and list them via listnotes. They use these details to trigger other tasks, though they must rely on action item tools to make modifications.

Q: How do CrewAI agents handle task assignment in Fellow?

Your crew's coordinator agent calls listusers to find the correct team member's email. It then passes that email to createactionitem to assign the task during workflow execution.

Q: Can I restrict which Fellow tools a CrewAI agent can use?

Yes, you can use MCPServerHTTP with a toolfilter to only expose safe tools like listmeetings to your agents. This prevents autonomous agents from accidentally running write operations like completeactionitem.

Q: Where is my Fellow meeting note data stored during CrewAI execution?

Your raw meeting note text fetched via getnote is held in ephemeral memory during the crew's MCP execution cycle. It is never persisted on Vinkius disks, ensuring your internal operational data remains private.

Coordinate multi-agent teams using CrewAI to manage your meeting agendas and tasks via the Fellow MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to CrewAI

Create your Vinkius account to connect Fellow 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 Fellow with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous workspace audits with CrewAI

`list_meetings` lets your CrewAI manager agent scan recent calendar events to coordinate downstream tasks. The manager agent delegates specific meetings to researcher agents for deep analysis. A researcher agent then calls `get_meeting` to extract the full agenda. This collaborative approach ensures your entire meeting history is parsed without manual overhead.

Resolve workspace tasks using an MCP Server

`list_action_items` provides your specialized CrewAI agents with a complete list of outstanding workspace tasks. One agent can filter for pending items while another prepares updates. Once a task is verified, the action agent executes `complete_action_item` to close the loop. The MCP Server ensures all tasks stay synced across agents.

Generate meeting agendas with specialized CrewAI teams

`create_action_item` allows your execution agent to assign new tasks directly to team members by email. The agent coordinates with a supervisor agent to ensure the due dates align with project milestones. By checking `list_users`, the crew matches emails to active workspace members before creating any items. This prevents broken assignments and keeps your team directories clean.

Setup guide

Set up Fellow 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 Fellow tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius HTTP endpoint URL directly into the agent's `mcps` list during initialization. This instantly exposes tools like `get_note` and `list_streams` to that specific agent.

CrewAI agents can read notes using `get_note` and list them via `list_notes`. They use these details to trigger other tasks, though they must rely on action item tools to make modifications.

Your crew's coordinator agent calls `list_users` to find the correct team member's email. It then passes that email to `create_action_item` to assign the task during workflow execution.

Yes, you can use `MCPServerHTTP` with a `tool_filter` to only expose safe tools like `list_meetings` to your agents. This prevents autonomous agents from accidentally running write operations like `complete_action_item`.

Your raw meeting note text fetched via `get_note` is held in ephemeral memory during the crew's MCP execution cycle. It is never persisted on Vinkius disks, ensuring your internal operational data remains private.

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