How to Use the Knorish MCP in Pydantic AI

Build type-safe student enrollment pipelines in Pydantic AI with strict runtime validation for Knorish.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knorish MCP to Pydantic AI

Create your Vinkius account to connect Knorish 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 Knorish with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate student data with Pydantic AI

This MCP Server uses `create_user` and `enroll_user` to register students while enforcing strict schema validation at the runtime boundary. If the academy API returns an unexpected payload structure, Pydantic AI raises a validation error immediately. This prevents silent data corruption in your database. Your agent processes user registrations knowing that every email, name, and student ID matches the exact type definition before executing downstream code.

Type-safe progress tracking in Pydantic AI

This MCP Server relies on `get_student_progress` to fetch real-time completion data from your online school. The framework parses this data against typed Python models, ensuring that course progress percentages are always valid floats. By avoiding string-based JSON parsing, you eliminate common runtime bugs in your reporting scripts. Your agent safely evaluates student engagement metrics without risking application crashes from unexpected null values.

Structured webhook setups and course lookups

This MCP Server exposes `list_webhooks` and `list_bundles` to structure your external application integrations. Every returned course bundle is validated against a strict schema, making it easy to display pricing and package details in your custom web apps. You initialize the connection using the HTTP toolset class and pass it to your Agent. The framework handles the underlying HTTP transport while verifying that Knorish endpoints match your local data definitions.

Setup guide

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

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

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

The framework intercepts responses from tools like the user details tool and validates them against Pydantic models at runtime. If the API schema changes, the agent throws a loud validation error instead of passing bad data.

Install the slim package with MCP support, then instantiate the toolset with your Vinkius server URL. Pass this toolset directly into your Agent constructor using the toolsets parameter.

Yes, the framework is model-agnostic. You can run the academy management tools with OpenAI, Anthropic, or local models running on your own hardware.

Pydantic AI catches the null field and checks if your model allows it. If it violates the type definition, the framework raises a validation error, allowing your agent to handle the exception gracefully.

Vinkius processes all requests inside isolated V8 sandboxes that self-destruct after execution. This keeps your school settings and admin tokens completely isolated, preventing unauthorized access during tool execution.

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