How to Use the Pando MCP in Pydantic AI

Q: Can I use Pydantic AI to build autonomous dispatchers with Pando?

Yes, you can build agents that run createindent autonomously. Because the framework enforces strict types, your agents cannot execute a booking without all required fields.

Build type-safe freight dispatch pipelines with Pydantic AI validating every carrier and route.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pando MCP to Pydantic AI

Create your Vinkius account to connect Pando to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pando with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe indent creation with Pydantic AI

The `create_indent` tool integrates with your Pydantic AI agents using the MCP Server to guarantee that every freight booking matches your strict schemas. If your agent attempts to submit an indent with missing vehicle parameters, the framework catches the error at runtime. This strict validation prevents malformed payloads from ever hitting your logistics API. You get clean, predictable data execution without silent failures in your dispatch loop.

Validate carrier lists and vehicle details

The `list_carriers` tool returns structured transport partner data that your agent parses against strict Python models. This ensures your code always knows exactly what fields to expect when evaluating carrier performance. It works hand-in-hand with `list_vehicles` to verify that every truck type matches your physical loading dock requirements. By enforcing these types, you avoid booking mismatched trailers.

Safe shipment tracking with runtime checks

The `get_shipment_details` tool fetches live transit data via MCP before passing it to your LLM. This prevents model hallucinations when reading complex cargo tracking statuses. Your agent can safely loop through `list_shipments` to compile status reports, knowing that any unexpected API response will trigger an immediate, readable validation error instead of corrupting your dashboard.

Setup guide

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

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

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

The framework wraps the MCP Server tools in strict Python type definitions. When you call `get_indent_details`, the response is parsed against a Pydantic model to guarantee schema compliance.

Yes, you can build agents that run `create_indent` autonomously. Because the framework enforces strict types, your agents cannot execute a booking without all required fields.

If a field like carrier assignment is null but marked as required, the SDK throws a validation error. This prevents your agent from making decisions based on incomplete tracking data.

You instantiate the MCP toolset with the HTTP URL provided by Vinkius. Pass this toolset directly to your Agent constructor to expose all logistics functions instantly.

All transaction payloads are processed within an isolated V8 sandbox that destroys runtime memory immediately after execution. Your logistics telemetry and partner contracts are never cached on disk.

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