How to Use the Navisphere MCP in Pydantic AI

Q: How do I register the Navisphere MCP Server in Pydantic AI?

Install the pydantic-ai-slimmcp package and instantiate MCPToolset with your Vinkius HTTP endpoint. Pass this toolset to your agent's toolsets argument, and it will automatically discover tools like searchavailableloads.

Q: How does the Navisphere MCP Server handle tracking in Pydantic AI?

Your agent calls trackshipment to fetch current status details. Pydantic AI coerces the API's coordinates and timestamps into clean Python datatypes, giving you structured data you can immediately pass to your database.

Q: How is my lane pricing and rate estimate data protected?

Every rate estimate pulled via getrateestimate and load detail from getloaddetails is processed in a secure, zero-trust V8 isolate. Your proprietary pricing models and private freight rates are never logged or exposed to third parties.

Build type-safe logistics loops with Pydantic AI to validate every freight bid and shipment update at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Navisphere MCP to Pydantic AI

Create your Vinkius account to connect Navisphere 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 Navisphere with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Freight Procurement

The `search_available_loads` tool queries active Navisphere freight listings using structured parameters. By running this through Pydantic AI, every returned load object is validated against strict Python schemas, preventing your agent from processing corrupted Navisphere load data. When you find a match, `get_load_details` pulls full specifications for that specific Navisphere load. If the Navisphere API returns unexpected fields, Pydantic AI raises an immediate validation error instead of letting your agent make decisions on bad data.

Verified Bidding with MCP Server

Submitting offers becomes completely predictable when your agent invokes `submit_bid` to place a pricing proposal on Navisphere. This MCP Server ensures that bid structures, currency formats, and load IDs match Navisphere's exact API expectations before the payload leaves your server. Once your bid wins, the agent calls `accept_offer` to confirm the Navisphere booking. Because Pydantic AI enforces type correctness, you never have to worry about silent booking failures when submitting bids to Navisphere.

Strict Status and Document Updates

Updating active freight progress is handled by `update_shipment_status` to change milestones like Arrived or Departed on Navisphere. Your Pydantic AI agent validates the shipment state against your internal state machine, ensuring you only push valid updates to Navisphere. For paperwork, `upload_shipment_documents` pushes PDFs and images directly to the active Navisphere shipment record. Pydantic AI validates the file metadata at runtime, making sure your system never uploads corrupted files to Navisphere.

Setup guide

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

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

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

Install the `pydantic-ai-slim[mcp]` package and instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset to your agent's `toolsets` argument, and it will automatically discover tools like `search_available_loads`.

The framework will immediately raise a validation error at runtime. This prevents your agent from acting on malformed `get_rate_estimate` outputs, ensuring your logistics pipeline fails safely instead of making wrong decisions.

Your agent calls `track_shipment` to fetch current status details. Pydantic AI coerces the API's coordinates and timestamps into clean Python datatypes, giving you structured data you can immediately pass to your database.

Yes, Pydantic AI is model-agnostic. You can run your logistics agent with Gemini, Anthropic, or local models while using the exact same tools like `create_shipment` to book freight.

Every rate estimate pulled via `get_rate_estimate` and load detail from `get_load_details` is processed in a secure, zero-trust V8 isolate. Your proprietary pricing models and private freight rates are never logged or exposed to third parties.

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