How to Use the DOD Contracts (FPDS) MCP in Google ADK

Q: How do I initialize the DOD Contracts (FPDS) toolset within a Google ADK agent?

Import McpToolset from the google-adk package and pass the MCP endpoint's HTTP URL. Then, include this toolset in the tools list when creating your LlmAgent instance.

Q: Can I restrict my agent to only use the contract search tool?

Yes, you can use the optional toolnames filter parameter when setting up your toolset in Python. This limits the agent's exposure to only the specific search endpoint exposed by the MCP Server.

Feed massive DOD procurement XML datasets directly into Gemini's million-token context window with this 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 Google ADK

Create your Vinkius account to connect DOD Contracts (FPDS) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject FPDS contract data into Google ADK pipelines

Connecting Gemini models to federal data is straightforward with the `search_contracts` tool. By using this MCP Server, your enterprise agent can query defense transactions with `DEPARTMENT_ID:"9700"` and parse the resulting XML payloads natively. You configure this connection by registering `McpToolset` with your HTTP server parameters in Python. The Google ADK translates the tool schema, making it immediately available for your `LlmAgent` to invoke during complex research tasks.

Analyze massive procurement histories with long context

The `search_contracts` tool feeds raw XML payloads directly into Gemini's context window. You don't need to build aggressive truncation scripts to fit raw FPDS feeds into the context window. The agent can cross-reference multiple historical defense transactions directly within its working memory. This allows it to spot long-term spending patterns across different military agencies without forgetting earlier search results.

Export contract intelligence straight to BigQuery

Exporting federal contract records directly into BigQuery tables is a core strength of the `search_contracts` tool. This sets up an automated pipeline where Gemini extracts structured fields from the raw feed and writes them to your cloud warehouse. You can restrict the agent's access by applying a `tool_names` filter to the toolset registration. This ensures your enterprise pipeline only exposes the specific contract search function, keeping your cloud environment secure.

Setup guide

Set up DOD Contracts (FPDS) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with DOD Contracts (FPDS) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="DOD Contracts (FPDS)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to DOD Contracts (FPDS) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Import `McpToolset` from the `google-adk` package and pass the MCP endpoint's HTTP URL. Then, include this toolset in the `tools` list when creating your `LlmAgent` instance.

Yes, your agent can use Gemini's reasoning to compare raw XML returned by `search_contracts` with your internal market intelligence stored in BigQuery. This makes it easy to flag new opportunities that match your historical bidding data.

Gemini's large context window easily accommodates the verbose XML payloads returned by `search_contracts`. You don't have to write complex parsing code; the model reads the entire feed structure directly.

Yes, you can use the optional `tool_names` filter parameter when setting up your toolset in Python. This limits the agent's exposure to only the specific search endpoint exposed by the MCP Server.

Your FPDS query parameters and returned XML contract entries are processed inside an isolated, zero-trust V8 sandbox. No procurement query history is stored or used for model training, keeping your competitive bidding strategies 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