Compatible with every major AI agent and IDE
What is the HUD Fair Market Rents MCP Server?
Connect directly to the U.S. Department of Housing and Urban Development (HUD) API to retrieve critical housing and economic data through natural conversation. This server provides comprehensive access to Fair Market Rents (FMR) and Income Limits (IL) across the United States.
What you can do
- Geographic Discovery — List all states, counties, and metropolitan areas with their corresponding FIPS and CBSA codes.
- Fair Market Rents (FMR) — Fetch detailed rent data for specific counties or metro areas, or retrieve entire statewide datasets for comparative analysis.
- Income Limits (IL) — Access median income data and limits for very low, extremely low, and low-income families by entity ID.
- MTSP Data — Retrieve Multifamily Tax Subsidy Project income limits for specific housing projects.
- Historical Analysis — Query data for specific years to track housing market trends.
How it works
- Subscribe to this server
- Enter your HUD User API Key
- Start querying housing data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Real Estate Professionals — Quickly verify current market rents for property valuations and rental listings.
- Policy Analysts & Researchers — Gather large-scale housing data for economic research and urban planning.
- Housing Agencies — Instantly check income eligibility limits for housing assistance programs.
Built-in capabilities (8)
Get Fair Market Rent (FMR) data by entity ID
Get Income Limits (IL) data by entity ID
Get Multifamily Tax Subsidy Project (MTSP) Income Limits data
Get Statewide Fair Market Rent (FMR) data
Get Statewide Income Limits (IL) data
List all counties in a specific state
List all Metropolitan areas
List all states and territories
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 8 tools from HUD Fair Market Rents through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries HUD Fair Market Rents, 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
HUD Fair Market Rents in OpenAI Agents SDK
HUD Fair Market Rents and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect HUD Fair Market Rents 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 HUD Fair Market Rents in OpenAI Agents SDK
The HUD Fair Market Rents 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 8 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
HUD Fair Market Rents for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the HUD Fair Market Rents 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 find the specific ID for a county to get its rent data?
First, use the list_states tool to get the state code, then use list_counties with that code. This will provide you with the 10-digit FIPS code (entity ID) needed for the get_fmr_data tool.
Can I retrieve rent data for an entire state at once?
Yes! Use the get_state_fmr_data tool and provide the two-letter state code (e.g., 'NY' for New York). It will return FMR data for all metro areas and counties within that state.
What is the difference between IL and MTSP data?
IL data (get_il_data) refers to general Income Limits for housing assistance, while MTSP data (get_mtsp_il_data) specifically targets Multifamily Tax Subsidy Projects. Both can be queried using the same entity IDs.
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 →
Tencent TRTC
11 toolsBring Tencent's Dominant Real-Time Communications Engine to your AI workflow. Manage rooms, cloud recordings, and call metrics.

KanbanZone
8 toolsManage projects visually with multi-board Kanban views, WIP limits, and process metrics that streamline team delivery.

Browser Bookmarks Parser
1 toolsTurn messy Chrome, Safari, and Firefox bookmark HTML exports into clean, structured JSON data. Instantly allow your AI to organize your digital life and remove duplicate links.

Berg System CRM
12 toolsClose more deals with a CRM built for financial advisors that tracks client relationships, policies, and follow-ups.
