How to Use the Cedar AI MCP in Pydantic AI

Use Cedar AI with Pydantic AI for type-safe rail data processing that prevents hallucinated inventory records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cedar AI MCP to Pydantic AI

Create your Vinkius account to connect Cedar AI 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 Cedar AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate rail records with Pydantic AI

Every response from `get_railcar_details` gets checked against your schema. If the rail data is malformed, the agent stops immediately. You ensure data integrity across your entire rail management system. It prevents bad data from reaching your core logs.

Update work orders via Pydantic AI

Your agent calls `update_work_order` with strictly typed payloads. The server validates the request before committing it to the database. This removes the risk of silent errors. You know exactly what happens to every work order in your system.

Manage railcar status safely

Use `update_railcar_status` to toggle cars between loaded and empty states. The agent confirms the change matches your model expectations. This workflow keeps your inventory counts accurate. You get a reliable view of your yard at all times.

Setup guide

Set up Cedar AI 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": {
        "cedar-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

The server returns structured data that Pydantic AI checks against your models. If the server output fails validation, the agent throws a clear error.

Yes. By enforcing strict schemas on tool outputs, your agent cannot invent data. It only works with the values the server provides.

It is. Use the MCPToolset class with your HTTP endpoint. It supports the standard SSE and Streamable HTTP transports.

You define the models you want to use. The MCP toolset handles the mapping from the server response to your Python objects.

We treat your waybill data as ephemeral. No records are persisted, and the data is encrypted during the transit process.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.