How to Use the CPSC (Consumer Product Safety Commission) MCP in LlamaIndex

Q: What's the setup process for using the CPSC (Consumer Product Safety Commission) tool with LlamaIndex?

It's straightforward. You'll use the McpToolSpec to wrap the client connection. This exposes the searchrecalls tool in a format that LlamaIndex agents can immediately use in a query engine or agent loop.

Q: Does this MCP server provide access to anything besides CPSC recalls?

No, this server is focused only on the CPSC searchrecalls endpoint. It provides a reliable, managed connection for building applications specifically around that dataset.

Build a RAG app with LlamaIndex that answers questions using an always-current index of CPSC product recall data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CPSC (Consumer Product Safety Commission) MCP to LlamaIndex

Create your Vinkius account to connect CPSC (Consumer Product Safety Commission) to LlamaIndex 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 CPSC (Consumer Product Safety Commission) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn CPSC Recalls into a Knowledge Base

The `search_recalls` tool lets your LlamaIndex application query the CPSC database. But the real point is what happens next: LlamaIndex automatically indexes the results into a vector store. Now, your agent's future queries are faster and smarter. It can perform semantic searches over all past recall data it has fetched, finding related hazards or products without hitting the live API every single time.

Ground Your Agent's Answers in Facts

Stop your agent from guessing about product safety. By using `search_recalls` within a RAG pipeline, your agent's responses are based on actual data pulled from the CPSC. When a user asks, "Is product X safe?", your LlamaIndex agent can query its indexed CPSC data and provide an answer with a direct citation to the official recall notice. It's proof, not just a plausible-sounding answer.

Query Recall Data via this MCP Server

Once the data from `search_recalls` is indexed, you can ask complex questions. For example, "Show me all toy recalls from last quarter related to choking hazards." This is way beyond a simple keyword search. LlamaIndex translates your natural language query into a search across the vectorized CPSC data. This MCP connection gives you the raw material, and LlamaIndex gives you a powerful way to analyze it.

Setup guide

Set up CPSC (Consumer Product Safety Commission) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all CPSC (Consumer Product Safety Commission) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to CPSC (Consumer Product Safety Commission) tools.",
)
response = await agent.run("List recent CPSC (Consumer Product Safety Commission) data")

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 CPSC. 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 CPSC (Consumer Product Safety Commission) 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 CPSC (Consumer Product Safety Commission) MCP in LlamaIndex

You can set up your LlamaIndex application to periodically run `search_recalls` for new data. It then updates your vector index with the latest recall information from the CPSC, keeping your knowledge base fresh.

Absolutely. Once the recall data is indexed, you can query it by any field, including manufacturer, hazard type, or date range. Your agent can answer specific, detailed questions about the CPSC data it has processed.

It's straightforward. You'll use the `McpToolSpec` to wrap the client connection. This exposes the `search_recalls` tool in a format that LlamaIndex agents can immediately use in a query engine or agent loop.

No, this server is focused only on the CPSC `search_recalls` endpoint. It provides a reliable, managed connection for building applications specifically around that dataset.

The recall data is public. Your agent's queries to get that data are processed in a Vinkius V8 Isolate sandbox. This means the request is handled in a temporary, memory-safe environment that is destroyed after use, preventing any part of your application state from persisting on the server.

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