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

Q: How can AutoGen help analyze spending patterns using USAspending (Federal Spending)?

You'll use searchspendingbycategory to filter data by criteria. By setting up agents, you can make them debate the best filtering parameters—should they prioritize CFDA or agency? The consensus is a highly targeted search query.

Q: Can AutoGen manage complex USAspending (Federal Spending) reporting for large organizations?

Yes. You'll combine getagencysubagencies to map out all small offices, then feed that list into multiple threads of discussion. The agents debate the proper consolidation method for accurate total spending.

Q: What is the process for investigating recipient details using USAspending (Federal Spending) with AutoGen?

An agent can query autocompleterecipient to get a potential match, then use getrecipient. A second agent challenges the data by cross-referencing the recipient's state information via getrecipientstate, ensuring the record is fully validated.

Q: What tools are needed for AutoGen to track spending over time using USAspending (Federal Spending)?

You need searchspendingovertime for aggregated amounts, and also getagencyawardscount. The agents will debate whether the count or the aggregation offers a more accurate measure of growth year-over-year.

Get consensus reports on federal spending using AutoGen's multi-agent debate framework.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auditing full award lifecycles with MCP Server.

To audit an entire grant, your agent first uses `get_award` to get the initial details. It then calls `get_subawards` and finally `get_transactions`. These tools provide a complete view of funding disbursement. The AutoGen framework lets you set up agents—one focused on compliance, one on finance—to debate whether the recorded transactions align with the original award parameters.

Comparing agency spending and budgets using AutoGen.

You can initiate a comparison by running `get_agency_awards` for current obligations. Simultaneously, run `get_agency_budgetary_resources` to check the allocated budget against those obligations. The agents then debate the discrepancy: Is the shortfall planned? Was the award count (`get_agency_awards_count`) misleading? They converge on a reasoned explanation.

Vetting disaster funding claims with AutoGen.

Use `get_disaster_overview` to gather general emergency context. Then, feed the specific data from `get_disaster_award_amount` into two debating agents: a 'Risk Agent' and an 'Outlay Agent.' The agents challenge each other on whether the reported outlay genuinely matches the scope of the disaster award funding provided.

Setup guide

Set up USAspending (Federal Spending) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes USAspending (Federal Spending) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="USAspending (Federal Spending)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent USAspending (Federal Spending) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="USAspending (Federal Spending)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent USAspending (Federal Spending) data")
    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 AutoGen

You'll use `search_spending_by_category` to filter data by criteria. By setting up agents, you can make them debate the best filtering parameters—should they prioritize CFDA or agency? The consensus is a highly targeted search query.

Yes. You'll combine `get_agency_sub_agencies` to map out all small offices, then feed that list into multiple threads of discussion. The agents debate the proper consolidation method for accurate total spending.

An agent can query `autocomplete_recipient` to get a potential match, then use `get_recipient`. A second agent challenges the data by cross-referencing the recipient's state information via `get_recipient_state`, ensuring the record is fully validated.

You need `search_spending_over_time` for aggregated amounts, and also `get_agency_awards_count`. The agents will debate whether the count or the aggregation offers a more accurate measure of growth year-over-year.

The server manages detailed financial records including award identifiers, budgetary resources, transaction amounts, recipient names, and crosswalk dictionary structures. This breadth allows the agents to build comprehensive arguments.

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