How to Use the GSA Per Diem Rates MCP in Pydantic AI

Q: Can I query rates by ZIP code using GSA Per Diem Rates in Pydantic AI?

Yes, the agent calls the getratesbyzip tool to fetch lodging and meal limits for a specific ZIP code. The framework validates the returned rates against your defined Pydantic models to ensure data integrity.

Q: How does Pydantic AI handle invalid locations when using GSA Per Diem Rates?

If you query an invalid location using getratesbycity, the server returns a clear error or empty schema. Pydantic AI catches this validation failure immediately, allowing your agent to prompt the user for a corrected city name.

Validate federal travel and lodging rates at runtime using Pydantic AI to guarantee compliance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GSA Per Diem Rates MCP to Pydantic AI

Create your Vinkius account to connect GSA Per Diem Rates 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 GSA Per Diem Rates with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce type-safe lodging lookups in Pydantic AI.

The `get_conus_lodging` tool pulls standard continental United States lodging rates for a specific fiscal year. Because this runs through Pydantic AI, the returned rate data is strictly validated against Python type models at runtime. If the external API returns an unexpected data type or missing fields, the framework raises a validation error immediately. This prevents your agent from passing corrupt or incomplete rate data to your accounting software.

Verify city-specific rates with strict schemas.

The `get_rates_by_city` tool fetches lodging and meal limits using a city name and state abbreviation. Your agent processes these inputs and guarantees that the response matches your exact database schema before proceeding. This MCP Server integration prevents silent failures when querying locations with ambiguous names. If a city name matches multiple regions, the validation layer forces the agent to resolve the ambiguity rather than guessing.

Audit meal breakdowns with absolute accuracy.

The `get_mie_breakdown` tool provides the exact breakfast, lunch, and dinner allocations for a given year. This MCP tool is used by your agent to verify individual meal receipts against the official federal maximums. Pydantic AI ensures that every numeric value in the breakdown is parsed as a precise decimal or integer. This eliminates rounding errors that often occur when agents handle raw JSON strings, keeping your financial audits accurate.

Setup guide

Set up GSA Per Diem Rates 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": {
        "gsa-per-diem-rates-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent GSA Per Diem Rates 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 GSA. 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 GSA Per Diem Rates 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 GSA Per Diem Rates MCP in Pydantic AI

You instantiate a unified MCP toolset with the server's HTTP endpoint and pass it to your agent's `toolsets` parameter. Pydantic AI automatically handles the connection and validates the tools.

Yes, the agent calls the `get_rates_by_zip` tool to fetch lodging and meal limits for a specific ZIP code. The framework validates the returned rates against your defined Pydantic models to ensure data integrity.

If you query an invalid location using `get_rates_by_city`, the server returns a clear error or empty schema. Pydantic AI catches this validation failure immediately, allowing your agent to prompt the user for a corrected city name.

The MCP Server requires an active connection to fetch the latest rates, but you can mock the tool responses in your Pydantic AI test suite. This allows you to verify your agent's routing logic without making live network calls.

The lookup tools only process public geographic parameters like ZIP codes, cities, and states. The server runs in an ephemeral V8 sandbox on Vinkius, ensuring your proprietary travel databases and employee records are never exposed during the rate validation process.

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