How to Use the USAspending (Federal Spending) MCP in Pydantic AI

Q: Can I use USAspending (Federal Spending) data with Pydantic AI for recipient lists?

Yes, the listrecipients tool provides a full list. Your agent uses this and other tools like getrecipient to pull verified details about specific entities while maintaining strict type safety.

Q: How does USAspending (Federal Spending) help with spending trends using Pydantic AI?

You can query historical data using searchspendingovertime. Because Pydantic AI validates these time series amounts, your agent treats the trend data as reliable and structured for immediate analysis.

Guarantee spending data accuracy for federal grants with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USAspending (Federal Spending) MCP to Pydantic AI

Create your Vinkius account to connect USAspending (Federal Spending) 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 USAspending (Federal Spending) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify agency financial structures.

Before you trust any number, you need it typed correctly. Use `get_agency_overview` to pull the foundational details of an agency. Furthermore, you can check its sub-agencies and obligated amounts using `get_agency_sub_agencies`. Pydantic AI validates every single field returned from this MCP Server against a strict schema. This means if the API sends unexpected data—like a missing date or wrong format—your agent fails LOUDLY, preventing silent corruption.

Audit spending by category.

Don't just query by recipient name; filter by federal program. The `search_spending_by_category` tool lets you narrow down data using criteria like CFDA or agency type. This is how your agent performs targeted audits. Pydantic AI ensures that the output structure for these complex searches—whether it’s a list of awards or aggregated amounts—is always predictable and correct, making downstream processing reliable.

Trace funds from source to final grant.

To trace money, you need multiple data points. Your agent can use `get_award` for the primary details, then follow up with `get_subawards` to see how those funds were split out. Pydantic AI’s strength shines here: when combining results from several tools like this MCP Server, it guarantees that the merged dataset remains type-safe. You always know your data structure is sound.

Setup guide

Set up USAspending (Federal Spending) 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": {
        "usaspending-federal-spending-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent USAspending (Federal Spending) 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 USAspending. 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 USAspending (Federal Spending) 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 USAspending (Federal Spending) MCP in Pydantic AI

Your agent calls the MCP Server tools, and Pydantic AI validates every response at runtime. This means you get guaranteed data types—no more hallucinated fields or unexpected JSON structures.

Yes, the `list_recipients` tool provides a full list. Your agent uses this and other tools like `get_recipient` to pull verified details about specific entities while maintaining strict type safety.

The server handles everything from award types and glossary terms (`get_glossary`) to detailed transaction records. Pydantic AI ensures that regardless of which tool you use, the output is always predictable.

You can query historical data using `search_spending_over_time`. Because Pydantic AI validates these time series amounts, your agent treats the trend data as reliable and structured for immediate analysis.

The server touches specific award funding details and transaction records. The primary benefit of using Pydantic AI is the guaranteed structural integrity of this sensitive financial data.

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