How to Use the DOD Contracts (FPDS) MCP in Pydantic AI

Q: How do I connect the DOD Contracts (FPDS) server to a Pydantic AI agent?

Install pydantic-ai-slimmcp and use the MCPToolset class to point to the server's HTTP endpoint. Pass this toolset instance into the toolsets argument of your Agent constructor.

Q: Can I use SSE transport to stream DOD Contracts (FPDS) updates in Pydantic AI?

Yes, the MCPToolset class in Pydantic AI supports both Streamable HTTP and SSE transports. This allows you to handle long-running FPDS search queries over the MCP link without timing out.

Q: Where does the raw contract XML get processed?

The raw XML payloads fetched via searchcontracts are routed through Vinkius's secure, ephemeral V8 isolates. Your query parameters and returned federal award data are never stored, keeping your competitive intelligence private.

Validate raw DOD procurement XML data at runtime with type-safe schemas using this Pydantic AI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DOD Contracts (FPDS) MCP to Pydantic AI

Create your Vinkius account to connect DOD Contracts (FPDS) 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 DOD Contracts (FPDS) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe DOD contract search with Pydantic AI

Retrieving XML feeds containing federal procurement records is handled by the `search_contracts` tool. By hooking this MCP Server into your Pydantic AI agent, you can enforce strict schemas on the incoming XML data before your model ever processes it. You initialize the connection using the MCP integration toolset with your external server URL. The framework automatically registers the search tool, letting your agent run validated queries with `DEPARTMENT_ID:"9700"` to target military awards.

Fail loudly on malformed federal XML payloads

The `search_contracts` tool throws strict validation errors when federal feeds return unexpected formats. This prevents your agent from hallucinating contract values or processing corrupted transaction data. You get absolute correctness instead of silent failures when analyzing multi-million dollar defense programs. The runtime validation halts execution the second a field mismatch occurs.

Model-agnostic contract parsing pipelines

Running across different LLM backends is a native feature of the `search_contracts` tool when used with Pydantic AI's model-agnostic architecture. You can use Anthropic, OpenAI, or local models to parse the XML returned by the server without rewriting your validation logic. The framework handles the translation of the contract tool schema across all supported backends. This ensures your defense market intelligence pipeline remains stable even if you switch the underlying model provider.

Setup guide

Set up DOD Contracts (FPDS) 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": {
        "dod-contracts-fpds-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent DOD Contracts (FPDS) 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 FPDS. 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 DOD Contracts (FPDS) 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 DOD Contracts (FPDS) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the `MCPToolset` class to point to the server's HTTP endpoint. Pass this toolset instance into the `toolsets` argument of your `Agent` constructor.

You define a Pydantic schema matching the contract entries you expect. When `search_contracts` returns raw XML, the agent parses and validates the fields against your model, throwing an error if there's a type mismatch.

Yes, the `MCPToolset` class in Pydantic AI supports both Streamable HTTP and SSE transports. This allows you to handle long-running FPDS search queries over the MCP link without timing out.

Pydantic AI will catch the bad value during runtime validation if it violates your defined schema. The agent will halt execution immediately, preventing bad data from corrupting your analytics pipeline.

The raw XML payloads fetched via `search_contracts` are routed through Vinkius's secure, ephemeral V8 isolates. Your query parameters and returned federal award data are never stored, keeping your competitive intelligence private.

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