4,500+ servers built on MCP Fusion
Vinkius
Kargo logo
Vinkius
Pydantic AI logo

How to Use the Kargo MCP in Pydantic AI

Run type-safe logistics operations with Kargo and Pydantic AI to guarantee zero silent failures on your loading docks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Kargo MCP on Cursor AI Code Editor MCP Client Kargo MCP on Claude Desktop App MCP Integration Kargo MCP on OpenAI Agents SDK MCP Compatible Kargo MCP on Visual Studio Code MCP Extension Client Kargo MCP on GitHub Copilot AI Agent MCP Integration Kargo MCP on Google Gemini AI MCP Integration Kargo MCP on Lovable AI Development MCP Client Kargo MCP on Mistral AI Agents MCP Compatible Kargo MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Pydantic AI

Connect Kargo MCP to Pydantic AI

Create your Vinkius account to connect Kargo 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

Pydantic AI schema validation

Validating incoming shipment data is guaranteed when your Pydantic AI agent uses `get_shipment` to fetch records. When your agent calls `get_shipment` or `list_orders`, the data is parsed and checked immediately. If Kargo returns an unexpected null value or an altered field structure, your code raises a validation error instantly. This prevents corrupted shipping manifests from propagating through your warehouse management software.

Type-safe logistics syncing

Syncing data to your logistics endpoints is safe when your agent uses `update_logistics` to update statuses. When your agent uses `update_logistics` to sync data to the Kargo Unified Endpoint, Pydantic AI ensures the payload matches the exact schema before sending it. This prevents broken API calls and partial updates. If the agent tries to send a malformed location or status, the framework blocks the request at the client level, saving you from failed transactions and API errors.

Hardware status integrity

Monitoring physical dock gates is highly reliable when your agent queries `get_device_status` and `list_devices`. This MCP Server lets you monitor dock gates with absolute type safety. Your automation code never acts on ambiguous or corrupted state data because of this runtime check. You can trust that when the model reads a gate as active, the underlying data structure has been verified down to the exact data type.

Setup guide

Set up Kargo MCP in Pydantic AI

Prerequisites

  • Python 3.10+ installed
  • pydantic-ai-slim[fastmcp] package
  • Active Vinkius subscription with a valid endpoint token
  1. 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. 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. 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": {
        "kargo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kargo. 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.

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 Kargo MCP in Pydantic AI

Install the library with `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your Vinkius HTTP URL. Pass this toolset to your `Agent` constructor in the `toolsets` argument to instantly expose tools like `list_shipments` or `get_order`.
The framework will raise a validation error immediately. Unlike other libraries that silently pass malformed JSON, Pydantic AI ensures that any data from `get_carrier_info` or `list_payload_logs` matches your expected Python types before your agent can use it.
Yes, the framework supports both Streamable HTTP and SSE transports. You run the server externally, and Pydantic AI connects to the Vinkius endpoint, allowing your agent to query `list_facilities` safely over the web.
You do not need to configure complex auth headers in your Python code. Vinkius manages the authentication layer, meaning your Pydantic AI agent only needs a single endpoint token to securely run operations like `update_logistics`.
Absolutely. All data processed from `get_device_status` or `list_orders` is handled within a zero-trust, ephemeral V8 isolate sandbox managed by Vinkius. Your physical device states and customer orders are never stored or logged on Vinkius servers.

Start using the Kargo MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Kargo. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.