How to Use the USAspending (Federal Spending) MCP in LangChain

Q: How do I find out about new US spending awards using USAspending (Federal Spending) with LangChain?

Start by calling searchnewawardsovertime. This tool lists time periods where awards were granted. You can then take a specific date range and feed it into getagencyawards to pull the actual transaction summary for that period.

Q: What's the best way to track spending across multiple agencies using USAspending (Federal Spending) with LangChain?

You can list all top-tier agencies first using gettoptieragencies. Then, for each agency returned, run getagencyawards to get a summary of their obligations. This process lets your agent compile a cross-section view.

Q: Can LangChain help analyze spending related to disaster funding using USAspending (Federal Spending)?

Absolutely. You'll use getdisasteroverview for the general picture of emergency funds. For a deeper dive, running getdisasterawardamount gives you obligation and outlay aggregations specifically tied to those disaster awards.

Q: If I need recipient details for USAspending (Federal Spending), how does LangChain handle that?

You can use the autocompleterecipient tool first to narrow down a name using search text. Once you get an identifier, passing it to getrecipient pulls all the full, verified individual or organization details.

Build complex, multi-step spending analysis chains using LangChain.

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 LangChain

Create your Vinkius account to connect USAspending (Federal Spending) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conducting sequential USAspending (Federal Spending) research with LangChain.

The `search_spending_by_category` tool lets your agent filter awards by agency, recipient, or CFDA. You can start by identifying a top-tier agency using `get_toptier_agencies`, and then use that output to refine the search for specific funding categories. This chaining approach means you don't stop at the initial search results. The data gathered from one tool becomes the exact input parameter for the next, building a complete, auditable spending path.

Investigating detailed award financials using LangChain.

Need to know exactly what money went where? Call `get_award` with specific identifiers to get full details on an award. Following that up with the `get_transactions` tool lets your agent pull all related financial movements for that single award. By linking these calls, you trace a fund's entire lifecycle—from initial commitment through every transaction recorded against it.

Mapping geographic spending patterns with LangChain.

Use `search_spending_by_geography` to pinpoint how federal money is allocated across states, counties, or congressional districts. You'll get structured data that maps out spending hotspots. After identifying a region, your agent can use `get_agency_overview` to see which specific agencies are primary players in that area, completing the picture of who funded what and where.

Setup guide

Set up USAspending (Federal Spending) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes USAspending (Federal Spending) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "usaspending-federal-spending-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent USAspending (Federal Spending) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Start by calling `search_new_awards_over_time`. This tool lists time periods where awards were granted. You can then take a specific date range and feed it into `get_agency_awards` to pull the actual transaction summary for that period.

You can list all top-tier agencies first using `get_toptier_agencies`. Then, for each agency returned, run `get_agency_awards` to get a summary of their obligations. This process lets your agent compile a cross-section view.

Absolutely. You'll use `get_disaster_overview` for the general picture of emergency funds. For a deeper dive, running `get_disaster_award_amount` gives you obligation and outlay aggregations specifically tied to those disaster awards.

You can use the `autocomplete_recipient` tool first to narrow down a name using search text. Once you get an identifier, passing it to `get_recipient` pulls all the full, verified individual or organization details.

This server handles transactional records, including award amounts, obligations, subaward agreements, recipient names, and detailed agency budgetary resources. Essentially, it covers the entire financial lifecycle of federal spending.

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