How to Use the BLS Local — LAUS State & County Unemployment MCP in LangChain

Q: How do I configure the BLS Local — LAUS State & County Unemployment MCP Server inside LangChain?

Install the required packages using pip install langchain-mcp-adapters langgraph and initialize the client. You connect to the Vinkius endpoint using the MultiServerMCPClient and pass the tools directly to your agent constructor.

Q: Can my LangChain agent query multiple county codes at once with BLS Local — LAUS State & County Unemployment?

Yes, the querybls tool supports up to 50 concurrent lookbacks in a single call. Your agent can pass an array of up to 50 distinct Series IDs to compare county-level metrics in one go.

Feed raw county-level LAUS unemployment timeseries directly into your LangChain chains for live regional economic analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BLS Local — LAUS State & County Unemployment MCP to LangChain

Create your Vinkius account to connect BLS Local — LAUS State & County Unemployment 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 BLS Local — LAUS State & County Unemployment with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map regional economic trends in LangChain chains

The `query_bls` tool pulls raw timeseries data from the Local Area Unemployment Statistics program directly into your active chain. Your agent takes a list of numeric series IDs, executes the request, and pipes the historical unemployment rates straight to the next step in your LangGraph pipeline. LangSmith traces every step of this data retrieval, showing you the exact payload size and latency of your BLS queries. You don't have to guess if your agent passed the correct county codes; you see the raw inputs and outputs in your debugging dashboard instantly.

Run multi-step labor market analysis with this MCP Server

The `query_bls` tool lets your agent fetch up to 50 concurrent lookbacks in a single run. Instead of writing separate scripts for each county, your LangChain agent decides when to pull state data versus county data based on the user's prompt. This MCP Server handles the connection details so your agent can focus on comparing metropolitan unemployment spikes against state baselines. The resulting timeseries data flows directly into your downstream analysis blocks without manual formatting.

Build self-correcting BLS queries in LangChain

The `query_bls` tool requires explicit BLS Series IDs to return unemployment metrics. If your LangChain agent guesses a wrong code, the raw error returns to the chain, allowing the model to correct the Series ID and retry the query immediately. You configure this by passing the MCP tool list directly to your LangGraph agent constructor. The agent manages the state of the conversation, maintaining the history of the queried county codes so it never requests the same regional data twice.

Setup guide

Set up BLS Local — LAUS State & County Unemployment 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 BLS Local — LAUS State & County Unemployment 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({
    "bls-local-laus-state-county-unemployment-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 BLS Local — LAUS State & County Unemployment 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 Bureau of Labor Statistics. 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 BLS Local — LAUS State & County Unemployment 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 BLS Local — LAUS State & County Unemployment MCP in LangChain

Install the required packages using `pip install langchain-mcp-adapters langgraph` and initialize the client. You connect to the Vinkius endpoint using the `MultiServerMCPClient` and pass the tools directly to your agent constructor.

Yes, the `query_bls` tool supports up to 50 concurrent lookbacks in a single call. Your agent can pass an array of up to 50 distinct Series IDs to compare county-level metrics in one go.

LangSmith tracks the exact payload, latency, and token usage of the `query_bls` tool calls. You can inspect the precise JSON response from the BLS API to verify your agent parsed the county codes correctly.

The raw error message is sent back to your LangChain agent as tool output. This lets your agent inspect the failure, adjust its Series ID parameters, and try the request again without crashing your pipeline.

Your requests for county and state unemployment timeseries run through an isolated, zero-trust sandbox environment on Vinkius. No query history or series IDs are stored, keeping your economic research confidential.

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