How to Use the Trello MCP in Pydantic AI

Q: How can I search Trello cards using Pydantic AI?

Use searchcards. This tool accepts keywords and validates the returned card data against your schema. The output is always predictable, which is key for reliable agents.

Q: Does this MCP Server help with labeling Trello using Pydantic AI?

Yes. Run listlabels first to gather the IDs. Then, use addlabeltocard which ensures that both the label ID and card context are correctly typed before applying the label.

Q: What if I try to delete a card using Trello and Pydantic AI?

While deletecard exists, the system strongly advises updating cards to 'closed' instead. This keeps the record of the data type intact while marking it as inactive.

Get guaranteed data accuracy for Trello with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Trello to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Board and Card Retrieval via MCP Server

The `get_board` tool pulls all the necessary details for a specific board, structuring them into validated models. Similarly, running `get_card` gives you type-safe access to an individual card's attributes. These tools ensure that every field—like title or description—is exactly what your agent expects it to be.

Managing Trello State with Pydantic AI

To build out a project, the `create_card` tool makes sure new cards are validated against your defined schemas. If anything goes wrong with the input data, the agent fails immediately and loudly. The `update_card` function lets you change existing records. The system validates every field before committing changes, preventing silent corruption of your project state.

Listing Contents for Trello

You can pull a complete board status using `list_board_cards`. This tool gives you all cards across the entire board and validates that list. For column visibility, use `list_lists` to get the names of lists on a board. If you need members' details, `list_members` returns typed data for every person associated with the MCP Server.

Setup guide

Set up Trello MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "trello-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Trello tools.",
)

result = await agent.run("List recent Trello transactions")
print(result.output)

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 Pydantic AI

Use `search_cards`. This tool accepts keywords and validates the returned card data against your schema. The output is always predictable, which is key for reliable agents.

Yes. Run `list_labels` first to gather the IDs. Then, use `add_label_to_card` which ensures that both the label ID and card context are correctly typed before applying the label.

It handles Board or Card details, including structured fields like titles, descriptions, lists, and member identifiers. The core focus is on runtime type validation.

While `delete_card` exists, the system strongly advises updating cards to 'closed' instead. This keeps the record of the data type intact while marking it as inactive.

Because every response is validated against a Pydantic model at runtime, you never get hallucinated fields or unexpected formats. The agent knows exactly what kind of data it’s working with.

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