How to Use the CFPB Complaints MCP in Google ADK

Q: How can my Google ADK agent search the CFPB Complaints database?

Your Gemini agent uses the searchcomplaints tool from the McpToolset. You provide filters like company name or date range. The agent executes the search and gets the complaint data back for analysis, all within your Google Cloud environment.

Q: Can I use Google ADK to find CFPB Complaints with full narratives?

Yes, the getcomplaintswithnarrative tool is designed for that. Your agent can call this tool to get the detailed descriptions consumers wrote. This is perfect for feeding into a long-context Gemini model for sentiment analysis.

Q: What's the best way for a Google ADK agent to track new CFPB Complaints?

The getrecentcomplaints tool gives your agent a direct stream of the newest complaints. You can build a scheduled agent in Vertex AI that runs this check daily and flags any relevant entries for your team.

Connect Gemini agents to 13.8M+ financial complaints with Google ADK. Analyze public CFPB data alongside your own in BigQuery.

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 Google ADK

Create your Vinkius account to connect CFPB Complaints to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Large-Scale Complaint Analysis

This MCP Server gives your agent access to the entire CFPB complaints database. Use the `search_complaints` tool to filter millions of records by company, product, or issue. It’s direct access to a massive public dataset. The real power comes when you combine this with Google ADK. Your Gemini agent can pull data using `get_company_complaints`, hold it in its massive context window, and cross-reference it with your private data in BigQuery. It turns public data into enterprise intelligence.

Drill Down into Specific Incidents

Your agent isn't limited to broad searches. It can use `get_complaint` to fetch a single record by its ID or `get_complaints_by_product` to investigate every complaint about "Student loans" or "Credit reporting". This is for targeted analysis. Imagine a workflow: a query against your BigQuery data flags a company. Your Google ADK agent then uses this server to automatically pull that company's public complaint history with `get_company_complaints`. The results can be written back to Google Cloud Storage for your team to review.

Integrate Public Data with Google ADK

The `get_recent_complaints` tool lets you build a real-time feed of new issues. You can have an agent that monitors this feed for complaints against specific companies or about certain products. In Google ADK, you wrap this service in an `McpToolset`. This exposes all nine tools, like `get_complaints_with_narrative`, directly to your LlmAgent. You can even filter the tool list if your agent only needs a few specific functions for its task.

Setup guide

Set up CFPB Complaints MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CFPB Complaints tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CFPB Complaints_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CFPB Complaints tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Your Gemini agent uses the `search_complaints` tool from the McpToolset. You provide filters like company name or date range. The agent executes the search and gets the complaint data back for analysis, all within your Google Cloud environment.

Yes, the `get_complaints_with_narrative` tool is designed for that. Your agent can call this tool to get the detailed descriptions consumers wrote. This is perfect for feeding into a long-context Gemini model for sentiment analysis.

The `get_recent_complaints` tool gives your agent a direct stream of the newest complaints. You can build a scheduled agent in Vertex AI that runs this check daily and flags any relevant entries for your team.

It works alongside it. Your Google ADK agent can query your BigQuery tables, then use this MCP server to pull public CFPB complaint data for comparison or enrichment. The agent acts as the bridge between your private data and this public dataset.

Your agent queries public complaint data: product types, company names, issue summaries, and consumer narratives where available. The Vinkius platform isolates each request in a dedicated sandbox. All traffic is encrypted, and no logs of your queries are persisted.

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