Bring Federal Spending
to CrewAI
Learn how to connect USAspending (Federal Spending) to CrewAI and start using 32 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the USAspending (Federal Spending) MCP Server?
Connect to the official USAspending database and gain unprecedented transparency into how the United States government allocates its budget. This server allows any AI agent to query real-time federal financial data, from high-level agency overviews to specific contract details.
What you can do
- Agency Insights — Retrieve comprehensive overviews of toptier agencies, including their budgetary resources and obligations.
- Award Tracking — Search and filter through millions of federal awards, contracts, and grants using advanced criteria.
- Geographic Analysis — Break down spending by state, county, or congressional district to see where the money is going.
- Sub-Agency Breakdown — List specific offices and sub-agencies within a department to identify internal spending distribution.
- Historical Trends — Analyze spending and new award counts over time to identify fiscal patterns.
How it works
- Subscribe to this server
- Enter your USAspending API Key (if required for higher rate limits)
- Start auditing federal spending from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Policy Researchers — quickly gather data on agency obligations and budgetary resources for reports
- Journalists — track federal contracts and grants in specific regions or categories for investigative stories
- Data Analysts — export and analyze spending trends over time across different government sectors
Built-in capabilities (32)
Awarding agencies matching search text
Glossary terms matching search text
Locations based on search text
Recipient names and UEI based on search text
Generates ZIP file of award data in CSV
ZIP file for Awards, Subawards, and Transactions
Get summary of transactions and obligations for an agency
Count of award types for agencies in a fiscal year
Get budgetary resources and obligations by fiscal year
Get agency overview for details page
List sub-agencies and offices with obligated amounts
Get details about a specific award
Federal account and agency funding info for an award
Map of award types by grouping
JSON structure of the Rosetta Crosswalk Data Dictionary
Insights on agencies receiving disaster funding
Obligation and outlay aggregations for disaster awards
Overview of disaster/emergency funding and spending
Current status of a requested download job
List of glossary terms and definitions
Individual recipient details
Recipient details based on identifier
Basic information about a specified state
Subawards related to a specific parent award
All toptier agencies and relevant data
Transactions related to a specific parent award
List of recipients in the database
List of time periods with new awards
Search and filter awards
g., agency, recipient, CFDA). Grouped spending data for visualizations
Spending by state, county, or congressional district
Aggregated transaction amounts over time
Why CrewAI?
When paired with CrewAI, USAspending (Federal Spending) becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call USAspending (Federal Spending) tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
USAspending (Federal Spending) in CrewAI
USAspending (Federal Spending) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect USAspending (Federal Spending) to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for USAspending (Federal Spending) in CrewAI
The USAspending (Federal Spending) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 32 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
USAspending (Federal Spending) for CrewAI
Every tool call from CrewAI to the USAspending (Federal Spending) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I get an overview of a specific agency's spending?
Use the get_agency_overview tool by providing the agency's toptier code. The agent will return high-level data including total obligations and budgetary resources.
Can I see which sub-agencies are spending the most within a department?
Yes! The get_agency_sub_agencies tool lists all sub-agencies and offices associated with a toptier agency, along with their respective obligated amounts.
Is it possible to filter federal awards by geographic location?
Absolutely. Use search_spending_by_geography to aggregate spending data by state, county, or district, or use search_spending_by_award with geographic filters.
How does CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.
Explore More MCP Servers
View all →
Mapbox
8 toolsGeocode addresses, get directions, calculate distances and generate maps with Mapbox's location platform.
GrainSure
12 toolsAccess silo monitoring via GrainSure — track grain fill levels, usage rates, predicted days to empty, and manage deliveries from any AI agent.
Maropost
11 toolsAutomate marketing and commerce via Maropost — manage contacts, campaigns, and workflows.
Groove
12 toolsManage your customer support tickets via Groove — list conversations, reply to customers, and monitor agent activity directly via AI.