How to Use the Evolio MCP in Pydantic AI

Q: What's the setup for Evolio with Pydantic AI?

It's straightforward. After you pip install, you create an MCPToolset instance with your Vinkius server URL. Then you pass this toolset into your Agent's toolsets list. That's it.

Q: What happens if a tool like updatecase fails?

The MCPToolset will raise an exception. Your agent's code should include error handling to catch these failures, log them, and decide whether to retry the operation or alert a human.

Build type-safe coaching agents with Pydantic AI. Get structured, validated data from this MCP Server for every client, case, and task.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evolio MCP to Pydantic AI

Create your Vinkius account to connect Evolio 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 Evolio with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Data, Every Time

This MCP Server exposes 14 tools to manage your coaching practice. When your agent calls `get_client` or `get_case`, Pydantic AI automatically parses the JSON response into a Pydantic model. If the API ever returns data that doesn't match the expected schema — say, a field is missing or has the wrong type — your code will raise a `ValidationError` immediately. No more silent data corruption. You know the data you're working with is correct.

Model-Agnostic Case Management

Pydantic AI lets you use whatever LLM you want—OpenAI, Anthropic, Gemini, even a local model. The logic for interacting with Evolio stays the same. Your agent can still call `create_task` or `update_case` regardless of the brain behind it. This frees you from vendor lock-in. You can swap out the LLM for a more powerful or cost-effective one without rewriting all your code for managing client cases and tasks. The MCP integration provides a stable interface to Evolio.

Build Reliable Pydantic AI Agents

Build a workflow you can trust. Create an agent that runs daily, calls `list_cases_by_status` to find all 'pending_review' cases, and then uses `list_tasks_by_case` to generate a summary for the head coach. Because every single API call is validated, you can trust this automation to run without manual oversight. If an Evolio API update ever changed the structure of the `get_task` response, your agent would fail loudly instead of silently processing bad data.

Setup guide

Set up Evolio 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": {
        "evolio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Pydantic AI automatically generates Pydantic models from the Evolio MCP Server's OpenAPI spec. When your agent gets data from a tool like `get_case`, it's validated against that model. If it doesn't match, you get an immediate error.

Yes. Pydantic AI is model-agnostic. You can configure it with any compatible LLM, including local models run with Ollama or llama.cpp, and it will still be able to use the Evolio toolset to `create_task` or `list_clients`.

It's straightforward. After you `pip install`, you create an `MCPToolset` instance with your Vinkius server URL. Then you pass this toolset into your `Agent`'s `toolsets` list. That's it.

The `MCPToolset` will raise an exception. Your agent's code should include error handling to catch these failures, log them, and decide whether to retry the operation or alert a human.

No. The server only handles metadata about your Evolio cases, tasks, and clients. Tools like `list_case_files` or `list_client_files` only return file names and identifiers, not the file content itself. Each request is processed in an isolated environment and no data is persisted.

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