How to Use the CFPB Complaints MCP in Pydantic AI

Q: Can my Pydantic AI agent search for specific CFPB Complaints?

Yes, it uses the searchcomplaints tool. You can filter by product, company, state, and more. The key benefit is that the list of results is guaranteed to be type-safe before your code ever touches it.

Q: How do I get detailed narratives from CFPB Complaints using Pydantic AI?

Your agent calls the getcomplaintswithnarrative tool. Pydantic AI ensures that the response object, including the narrative string, is correctly formed before your agent processes it. You can trust the data structure you're working with.

Q: Is it possible to track complaint statistics with a Pydantic AI agent?

Definitely. The getcomplaintsstats tool provides quick counts. Your Pydantic AI agent can call this and trust that the returned integer count is exactly what it expects, preventing type errors downstream.

Get type-safe, validated access to the CFPB database with Pydantic AI. Build agents that won't fail silently on bad data.

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 Pydantic AI

Create your Vinkius account to connect CFPB Complaints to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Complaints with Guaranteed Structure

The `search_complaints` tool lets your agent query the 13.8M+ record CFPB database. You can filter by company, product, date range, and more. It's a direct line to a huge dataset. Here's the key: when the data comes back, Pydantic AI validates it against a model. If the API ever returns a malformed record or an unexpected field, your agent will raise a `ValidationError` immediately. No more silent data corruption in your application.

Reliable, Granular Data Access

Your agent can use `get_complaint(complaint_id=...)` to pull one specific record or `get_complaints_by_state` to get a list for a region. These tools give you precise access when you don't need a full-blown search. Every response from tools like `get_company_complaints` or `get_complaints_by_product` is checked at runtime. Pydantic AI ensures the list of complaints you get back actually matches the structure you expect. This makes your agent's logic simpler and far more robust.

Build a Correctness-First MCP Server

This MCP server exposes tools like `get_recent_complaints` and `get_complaints_with_narrative`. They let you track new issues or analyze detailed consumer stories, giving your agent more ways to understand the data. You just add the `MCPToolset` to your Pydantic AI agent, and it works. It doesn't matter if you're using OpenAI, Anthropic, or a local model. The validation happens on your side, giving you a consistent, reliable data layer for any agent you build.

Setup guide

Set up CFPB Complaints MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cfpb-complaints-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CFPB Complaints tools.",
)

result = await agent.run("List recent CFPB Complaints transactions")
print(result.output)

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 Pydantic AI

Pydantic AI automatically validates every API response against a predefined Pydantic model. If the data from a tool like `search_complaints` doesn't match the expected schema, it raises an exception. This prevents corrupted data from getting into your system.

Yes, it uses the `search_complaints` tool. You can filter by product, company, state, and more. The key benefit is that the list of results is guaranteed to be type-safe before your code ever touches it.

Your agent calls the `get_complaints_with_narrative` tool. Pydantic AI ensures that the response object, including the narrative string, is correctly formed before your agent processes it. You can trust the data structure you're working with.

Definitely. The `get_complaints_stats` tool provides quick counts. Your Pydantic AI agent can call this and trust that the returned integer count is exactly what it expects, preventing type errors downstream.

The connection only handles public CFPB data—company names, issue types, and complaint text. Vinkius processes each request in a stateless, sandboxed environment using a zero-trust model. Your API token is the only credential, and no query data is ever logged or stored.

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