How to Use the airfocus MCP in AutoGen

Q: How do I give my AutoGen agents access to airfocus?

Use the mcpservertools function from the autogen-extmcp package, pointing it to your Vinkius server URL. This returns a list of callable tools you can pass directly to your AssistantAgent constructors. AutoGen handles the schema and execution.

Assemble a team of AutoGen agents to debate, plan, and manage your airfocus product strategy through conversation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect airfocus MCP to AutoGen

Create your Vinkius account to connect airfocus 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 airfocus with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Product Planning

Build a group of specialized agents that collaborate on your roadmap. One agent, acting as a Product Manager, can propose a new feature with `create_airfocus_item`. Another agent, the QA Lead, can then use `list_airfocus_items` to check for similar existing items or potential conflicts. This isn't a linear process; it's a conversation. The agents debate the priority, scope, and impact. They can use `list_airfocus_fields` to understand your scoring system and argue their points before reaching a consensus on how to proceed with `update_airfocus_item`.

Debate and Refine Feature Ideas

AutoGen's strength is its conversational approach to problem-solving. You can task your agent group with refining a vague idea. They'll use `get_airfocus_item` to pull the current details, then discuss what's missing, what the risks are, and what the dependencies might be. The outcome is a well-vetted plan. One agent might suggest adding a 'technical_debt' tag, while another argues for a higher impact score. The final result, executed via `update_airfocus_item`, is a product of that debate, not a single command.

Automate Strategy Sessions with an AutoGen MCP Server

Set up an automated 'strategy review' where your agents meet. The 'Analyst' agent can pull all items from a workspace using `list_airfocus_items` and present a summary. The 'Strategist' agent can then identify items that no longer align with current goals. This MCP server provides the tools for that conversation. The agents don't just talk; they act. The discussion concludes with a series of `update_airfocus_item` calls to archive old ideas or reprioritize critical features, all based on the group's decision.

Setup guide

Set up airfocus 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 airfocus 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="airfocus_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent airfocus 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 airfocus. 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 airfocus 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 airfocus MCP in AutoGen

Use the `mcp_server_tools` function from the `autogen-ext[mcp]` package, pointing it to your Vinkius server URL. This returns a list of callable tools you can pass directly to your `AssistantAgent` constructors. AutoGen handles the schema and execution.

Yes, that's the whole point. You can equip a 'ProductManagerAgent' with `create_airfocus_item`, while a 'ResearcherAgent' only gets `list_airfocus_items`. The agents will then converse to solve problems that require multiple tools from the MCP server.

A great starting point is an 'idea triage' team. A user submits an idea, and a team of agents debates it. They check for duplicates in airfocus, score it using your custom fields, and decide whether to create a new item or merge it with an existing one.

The connection itself is stateless per call, which is safer. However, the state is maintained within the AutoGen conversation history. Agents remember previous tool calls and their results, allowing them to have a continuous, context-aware discussion about your airfocus data.

The agents can access and discuss your airfocus item data, workspace lists, and custom field definitions. All tool calls are routed through Vinkius's zero-trust infrastructure, which isolates each request. Data only exists for the duration of the API call.

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