How to Use the CFPB Complaints MCP in OpenAI Agents SDK

Q: How do I search CFPB Complaints using the OpenAI Agents SDK?

Your agent will use the searchcomplaints tool. You just need to provide the query parameters like company name or product type. The OpenAI Agents SDK handles the tool discovery and execution automatically.

Q: Can my agent get complaint narratives with this MCP Server?

Yes. The getcomplaintswithnarrative tool specifically fetches complaints that include the consumer's detailed story. You can filter these by product, company, or state to get the full context.

Q: What's the best way to analyze recent CFPB Complaints with the OpenAI Agents SDK?

Use the getrecentcomplaints tool for a direct feed of the latest entries. For statistical analysis, combine it with getcomplaintsstats to track volume changes over time. Your agent can automate this entire process.

Q: Can I filter CFPB Complaints by state in the OpenAI Agents SDK?

Absolutely. The getcomplaintsbystate tool lets your agent pull all complaints filed from a specific US state. The searchcomplaints tool also supports filtering by state, along with other criteria.

Build production agents that query the CFPB database using the OpenAI Agents SDK. Guardrails included.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CFPB Complaints MCP to OpenAI Agents SDK

Create your Vinkius account to connect CFPB Complaints to OpenAI Agents SDK 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 CFPB Complaints with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query 13.8M+ Financial Complaints

The `search_complaints` tool lets your agent dig through the entire CFPB database. You can filter by company, product type like "Mortgage", or even by specific issues. It's how you find patterns in consumer complaints without manual digging. With the OpenAI Agents SDK, these tools are discovered automatically. You can set up specialized agents—one for searching with `search_complaints`, another for specifics with `get_complaint`—and let the framework handle the handoff. Tracing is built-in, so you see every step.

Isolate Specific Data Points

Sometimes you don't need a broad search. Your agent can use `get_complaint` to pull a single record by its ID. Or use `get_complaints_by_state` and `get_complaints_by_issue` to zoom in on regional or product-specific problems. This is where the SDK's guardrails are critical. Before your agent executes `get_company_complaints` with a specific company name, you can validate the action. This prevents your production agent from pulling the wrong data or making unexpected calls from this MCP Server.

Track Trends with the OpenAI Agents SDK

Use `get_recent_complaints` to build a feed of new issues as they're filed. The `get_complaints_stats` tool gives you quick counts without pulling down thousands of records. It’s a fast way to get a high-level view. Your agent can run these checks on a schedule. Because the SDK caches the tool list, subsequent runs are faster. You build one agent to monitor trends, and if it spots an anomaly, it can hand off to another agent for a deep dive using more detailed search tools.

Setup guide

Set up CFPB Complaints MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CFPB Complaints tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CFPB Complaints tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CFPB Complaints tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CFPB Complaints Agent",
            instructions="You have access to CFPB Complaints tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 CFPB Consumer Complaint Database. 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 CFPB Complaints 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 CFPB Complaints MCP in OpenAI Agents SDK

Your agent will use the `search_complaints` tool. You just need to provide the query parameters like company name or product type. The OpenAI Agents SDK handles the tool discovery and execution automatically.

Yes. The `get_complaints_with_narrative` tool specifically fetches complaints that include the consumer's detailed story. You can filter these by product, company, or state to get the full context.

Use the `get_recent_complaints` tool for a direct feed of the latest entries. For statistical analysis, combine it with `get_complaints_stats` to track volume changes over time. Your agent can automate this entire process.

Absolutely. The `get_complaints_by_state` tool lets your agent pull all complaints filed from a specific US state. The `search_complaints` tool also supports filtering by state, along with other criteria.

The server only processes public CFPB complaint information like company names, product types, and issue descriptions. Vinkius runs the MCP Server in an ephemeral, zero-trust sandbox. Your connection is secured, and no session data is stored after the request is complete.

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