How to Use the Fellow MCP in AutoGen

Q: How do AutoGen agents coordinate when completing a Fellow task?

One agent retrieves the task with getactionitem while another verifies the work. They must both agree before the executor agent calls completeactionitem.

Q: Can I restrict which AutoGen agent has access to Fellow tools?

Yes. You can register tools like deletenote only with your admin agent, while leaving read-only tools like listnotes open to the entire group.

Q: What happens if an AutoGen agent tries to archive a Fellow item?

The agent calls archiveactionitem with the target ID. You can configure a supervisor agent to review and approve the archive request first.

Let your AutoGen agents debate project progress using live data from your 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 AutoGen

Create your Vinkius account to connect Fellow 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 Fellow with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate action item status with AutoGen agents

Set up a multi-agent conversation where one agent pulls tasks using `list_action_items` and another checks codebase commits. They can debate whether a task is actually ready for `complete_action_item`. This consensus-driven approach stops agents from closing tasks prematurely. It ensures that action items are only completed after thorough cross-verification.

Analyze meeting notes via MCP Server collaboration

Use `list_notes` and `get_note` to feed meeting context to a group of specialized agents. An editor agent and a developer agent can discuss the notes to plan the next sprint. This prevents single-agent bias when interpreting meeting outcomes. The agents work together to extract clear, actionable requirements from your documentation.

Review transcripts and recordings safely

When agents need deep context, they can call `get_transcript` to read what was actually said. If they need to clean up old files, they must agree before calling `delete_recording`. This setup uses AutoGen's multi-agent consensus to protect your data. The MCP Server ensures no single agent can delete a recording without other agents verifying that it is no longer needed.

Setup guide

Set up Fellow 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 Fellow 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="Fellow_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Fellow 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 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 AutoGen

One agent retrieves the task with `get_action_item` while another verifies the work. They must both agree before the executor agent calls `complete_action_item`.

Yes. You can register tools like `delete_note` only with your admin agent, while leaving read-only tools like `list_notes` open to the entire group.

The McpToolAdapter automatically translates the server's tool schemas into the format AutoGen expects, so your agents can call them without custom code.

The agent calls `archive_action_item` with the target ID. You can configure a supervisor agent to review and approve the archive request first.

Your meeting recordings and transcript data are retrieved on demand. This MCP Server runs in a secure V8 isolate sandbox on Vinkius, protecting your sensitive business conversations from external exposure.

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