How to Use the Trello MCP in AutoGen

Q: How do I use AutoGen to search Trello cards?

The Debate Agent uses searchcards initially. If the results are ambiguous, other agents challenge the keyword and suggest refining the search, leading to a more accurate final result.

Q: If I use AutoGen, how do I manage Trello labels?

One agent might call listlabels to get all options. Another might debate where these labels should go before the consensus calls addlabeltocard.

Q: Does AutoGen help with Trello data privacy?

Yes. The server touches user details via getme, giving the agents insight into who's logged in. This helps them debate permissions and ownership before making changes to a board.

Let agents debate and decide on Trello tasks using AutoGen's multi-agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Trello MCP to AutoGen

Create your Vinkius account to connect Trello 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 Trello with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deciding Card Status Changes

When a task needs to move, the Debate Agent can use `update_card`. One agent might argue it should be labeled 'Urgent,' while another argues for changing its status. The system converges on the best action, executing the update.

Consensus on Board Setup

If you need a new board or list structure, multiple agents can debate the optimal setup. One might call `list_boards` to check for existing boards, and another might decide that a new one is needed, calling `create_card` within it.

Complex Data Gathering

If multiple data points are required—say, the board owner (`get_me`) and all members (`list_members`)—the agents debate which calls to make. They run these tools sequentially until they achieve a complete picture of who is involved.

Setup guide

Set up Trello 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 Trello 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="Trello_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The Debate Agent uses `search_cards` initially. If the results are ambiguous, other agents challenge the keyword and suggest refining the search, leading to a more accurate final result.

One agent might call `list_labels` to get all options. Another might debate where these labels should go before the consensus calls `add_label_to_card`.

The agents can be tasked with listing all potential boards using `list_boards`. If they disagree on which ones are relevant, they debate the criteria until a final list is provided.

Yes. The server touches user details via `get_me`, giving the agents insight into who's logged in. This helps them debate permissions and ownership before making changes to a board.

The agents coordinate by first getting the board ID, then running `list_board_cards`. They validate that this single action provides all necessary card data before concluding the task.

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