How to Use the Ellie Planner MCP in Pydantic AI

Build type-safe planning workflows that validate Ellie Planner data at runtime using 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 Ellie Planner MCP to Pydantic AI

Create your Vinkius account to connect Ellie Planner 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 Ellie Planner with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Runtime Validation with Pydantic AI

The `get_task` tool returns highly structured task data that Pydantic AI immediately validates against strict Python models. If the server returns unexpected data formats, your application fails loudly and immediately, preventing corrupt data from entering your production systems. This type-safe approach ensures that every execution of `list_tasks` or `list_lists` complies with your exact schema definitions. You never have to worry about silent failures or hallucinated fields on your visual planning boards.

Safe Task Creation and Modification

The `create_task` tool requires specific inputs like title, dates, and labels, which are verified before the request ever leaves your Python code. By using this MCP Server, your agent cannot submit malformed tasks that would break your visual timeline. When updating timelines, the agent uses `update_task` with the exact parameter types expected by the planner. This guarantees your visual boards remain consistent and readable for the entire team.

Type-Safe Board Cleanup

The `complete_task` tool allows your agent to safely close out milestones once they meet your application's criteria. Because Pydantic AI enforces type safety, the agent cannot pass invalid task IDs to this tool. The same rigor applies when using `delete_task` or fetching labels with `list_labels`. Your agent interacts with your planning board through a bulletproof, type-checked interface that works across any LLM backend.

Setup guide

Set up Ellie Planner 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": {
        "ellie-planner-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Ellie Planner 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 Ellie Planner. 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 Ellie Planner 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 Ellie Planner MCP in Pydantic AI

Install the library using pip with the mcp extra, then instantiate MCPToolset pointing to your Vinkius HTTP server. Pass this toolset into the toolsets list when defining your Agent.

It supports both, but you must run the server externally as the framework uses HTTP or SSE transports. Vinkius hosts this server for you, giving you an endpoint to plug straight into your toolset configuration.

Pydantic AI raises a validation error immediately. This prevents your agent from parsing corrupted task lists or making incorrect planning decisions based on malformed payloads.

Yes, the framework is model-agnostic. You can use this server with Anthropic, Gemini, or local models, and still get the same strict type validation on every task and label.

Your task titles, deadlines, and project lists are transferred over encrypted SSE/HTTP connections directly between your runtime and the Vinkius sandbox. No data is stored or cached outside your authorized execution environment.

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