How to Use the BLS Wages — OEWS Occupational Employment MCP in LangChain

Q: Can I use LangSmith to debug my BLS Wages — OEWS Occupational Employment calls inside LangChain?

Yes, every time your LangChain agent invokes the querybls tool, LangSmith captures the exact series IDs requested and the raw wage timeseries returned. This makes it simple to spot formatting issues or invalid occupational codes.

Feed raw Bureau of Labor Statistics wage series directly into your LangChain pipelines to build data-driven HR agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BLS Wages — OEWS Occupational Employment MCP to LangChain

Create your Vinkius account to connect BLS Wages — OEWS Occupational Employment 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 Wages — OEWS Occupational Employment with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run batch salary lookups inside your LangChain agents

The `query_bls` tool exposes raw Bureau of Labor Statistics timeseries data directly to your multi-step chains. Your agents can now grab median earnings for up to 50 series IDs in a single step, feeding that raw data straight into subsequent prompt templates. You don't need to write custom API scrapers or handle raw HTTP errors inside your code. LangChain agents use this MCP Server to pull exact federal wage metrics, letting you build automated recruiting pipelines that evaluate market rates on the fly.

Trace wage calculations with LangSmith observability

LangChain developers can monitor every single `query_bls` payload to watch how the agent parses complex BLS series codes. This integration lets you trace latency and token usage for every wage query, making it easy to debug failed occupational code lookups. If an agent tries to compare a software engineer's salary in California against one in Texas, you'll see the exact inputs and outputs in your LangSmith dashboard. You get absolute visibility into how your chain maps raw occupational data to your final output.

Build automated HR chains using this MCP Server

This MCP Server exposes a single, high-throughput tool that lets your LangChain workflows fetch regional occupational data in parallel. By passing the tool list to your agent executor, you allow your system to dynamically decide when to pull federal salary baselines. You get a clean, structured JSON output containing historical wage trends. Your chains can immediately pass these numbers to a math tool or formatting node without manual data cleaning.

Setup guide

Set up BLS Wages — OEWS Occupational Employment 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 Wages — OEWS Occupational Employment 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-wages-oews-occupational-employment-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 Wages — OEWS Occupational Employment 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 Wages — OEWS Occupational Employment 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 Wages — OEWS Occupational Employment MCP in LangChain

Your LangChain agent passes up to 50 explicit BLS Series IDs to the `query_bls` tool in a single execution. The agent can then split these results across parallel chain steps or aggregate them into a single prompt context.

Yes, every time your LangChain agent invokes the `query_bls` tool, LangSmith captures the exact series IDs requested and the raw wage timeseries returned. This makes it simple to spot formatting issues or invalid occupational codes.

No, Vinkius manages the authentication layer for you. Your LangChain app connects to a single secure MCP endpoint, allowing all your chain runs to fetch occupational data without managing individual BLS credentials.

You should instruct your LangChain agent to identify the correct numerical series code before calling `query_bls`. Once the agent has the code, it passes it directly to the tool to fetch the exact median wage data.

No, this server only queries public federal data using public series IDs. Your internal salary records and LangChain prompt histories are executed inside Vinkius's secure sandbox and never stored or shared.

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