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

Q: Can I combine the CPSC (Consumer Product Safety Commission) data with my own database in LangChain?

Yes, that's a core use case. Your agent can use searchrecalls to get a recall notice, then use other MCP tools to find related items in your own systems. LangChain is built for exactly this kind of tool composition.

Q: Is this MCP server just for product recalls?

Yes, this server is specifically for the CPSC's searchrecalls tool. It provides a direct, managed connection to that public dataset. It's designed to do one job well.

Build compliance chains in LangChain that check CPSC recalls and react to safety alerts automatically.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Recall Checks into Workflows

Use the `search_recalls` tool as a link in your LangChain agent's logic. Your agent can take a product name from a database, query the CPSC for recalls, and then decide its next move based on the findings. For example, if `search_recalls` returns a "fire hazard," your chain could trigger another tool to open a high-priority ticket. If it finds nothing, it moves on. You're building automated compliance checks, not just one-off lookups.

Build Custom Compliance Agents

Give your ReAct agents the ability to query for product safety data. The `search_recalls` tool lets your agent investigate product lists, check supplier inventories, or validate marketplace listings against official CPSC data. Because LangChain can combine tools, your agent could find a recalled product and then use a different tool to search your internal inventory for that same item. This connects public safety data to your own operations.

Trace Every Query with this MCP Server

Every call your agent makes to the CPSC `search_recalls` tool is fully observable in LangSmith. You'll see the exact inputs, the raw output from the CPSC API, and how long the query took. This makes debugging your compliance chains simple. You can pinpoint exactly why an agent made a certain decision after a recall search, ensuring your automated logic is sound and auditable.

Setup guide

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

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CPSC (Consumer Product Safety Commission) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "cpsc-consumer-product-safety-commission-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CPSC (Consumer Product Safety Commission) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent can loop through a list of products, calling the `search_recalls` tool from this MCP Server for each one. You'd build a chain that takes a product list as input and outputs a report summarizing any recalls found.

Yes, that's a core use case. Your agent can use `search_recalls` to get a recall notice, then use other MCP tools to find related items in your own systems. LangChain is built for exactly this kind of tool composition.

Wrap the tool call in a try/except block within your chain's logic. LangChain agents can be designed to handle exceptions, allowing them to retry the CPSC query or trigger a fallback action, like notifying a human operator.

Yes, this server is specifically for the CPSC's `search_recalls` tool. It provides a direct, managed connection to that public dataset. It's designed to do one job well.

The CPSC data itself is public. Your query, containing product names or other search terms, passes through Vinkius's ephemeral, sandboxed environment. The connection is isolated, so nothing about your agent's session or other data is exposed to the public API endpoint.

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