Bring Us Treasury
to OpenAI Agents SDK
Learn how to connect Fiscal Data (U.S. Treasury) to OpenAI Agents SDK and start using 4 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 Fiscal Data (U.S. Treasury) MCP Server?
Connect directly to the U.S. Department of the Treasury's Fiscal Data API to retrieve authoritative financial information. This server enables AI agents to query a vast library of federal financial data for analysis, reporting, and economic research.
What you can do
- Comprehensive Data Access — Query any of the 170+ available endpoints including debt, interest rates, and federal spending via the
query_datasettool. - Exchange Rates — Fetch official Treasury Reporting Rates of Exchange for international currencies using
get_rates_of_exchange. - Monthly Treasury Statements — Access detailed summaries of federal receipts and outlays through
get_mts_table_1andget_mts_table_9. - Advanced Filtering — Apply precise filters, sorting, and pagination to handle large datasets efficiently directly within your conversation.
How it works
- Subscribe to this server
- (Optional) Enter your Fiscal Data API Key for higher rate limits
- Start querying federal financial data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Financial Analysts — instantly retrieve historical exchange rates and federal budget summaries without manual CSV downloads.
- Data Scientists — pull clean, structured fiscal data directly into your analysis environment.
- Policy Researchers — track government spending and debt metrics through natural language queries.
Built-in capabilities (4)
Get Monthly Treasury Statement (MTS) Table 1
Get Monthly Treasury Statement (MTS) Table 9
Get Treasury Reporting Rates of Exchange
Provide the endpoint path (e.g., v1/accounting/od/rates_of_exchange) and optional filters. Query any Fiscal Data dataset endpoint
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 4 tools from Fiscal Data (U.S. Treasury) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Fiscal Data (U.S. Treasury), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Fiscal Data (U.S. Treasury) in OpenAI Agents SDK
Fiscal Data (U.S. Treasury) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Fiscal Data (U.S. Treasury) to OpenAI Agents SDK 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 Fiscal Data (U.S. Treasury) in OpenAI Agents SDK
The Fiscal Data (U.S. Treasury) 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 4 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK 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
Fiscal Data (U.S. Treasury) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Fiscal Data (U.S. Treasury) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I access specific datasets like the national debt or federal spending?
You can use the query_dataset tool. Simply provide the endpoint path (e.g., 'v1/debt/mspd/mspd_table_1' for the Monthly Statement of the Public Debt) and any optional filters to get the exact data you need.
Can I filter the financial data by a specific date or currency?
Yes! All tools like get_rates_of_exchange and get_mts_table_1 support a filter parameter. For example, use record_date:eq:2023-12-31 to get data for a specific day or country_currency_desc:eq:CANADA-DOLLAR for specific currency rates.
What is the difference between Table 1 and Table 9 in the Monthly Treasury Statement?
The get_mts_table_1 tool provides a high-level summary of receipts, outlays, and the surplus or deficit. The get_mts_table_9 tool provides a more granular breakdown of Budgetary Receipts by reporting entity and major source.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
CFPB Complaints
9 toolsSearch 13.8M+ consumer complaints against financial companies — filter by product, company, state and issue.
Fastn
16 toolsAutomate and execute low-code workflows via Fastn — manage flow definitions, monitor executions, and handle connector credentials directly.
Mattermark
10 toolsStartup and venture capital data via Mattermark — search companies, investors, and funding rounds.
RentCast
8 toolsAutomate real estate data and valuation tracking via RentCast — manage properties, rental yields, and market trends directly from any AI agent.