How to Use the USAJOBS (OPM) MCP in LangChain

Q: How do I use the USAJOBS (OPM) MCP Server with LangChain?

You call the client's gettools() method and pass those tools to your ReAct agent. The agent then handles deciding which tool, like searchjobs, is necessary for the user query.

Build complex, multi-step reasoning pipelines for USAJOBS (OPM) using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect USAJOBS (OPM) MCP to LangChain

Create your Vinkius account to connect USAJOBS (OPM) 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 USAJOBS (OPM) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining Job Search with the MCP Server

The `search_jobs` tool lets your agent find active federal job openings. You can then pass the resulting list of jobs to another step, maybe using `get_announcement_text` to pull detailed requirements for a specific listing. This flow builds an entire reasoning chain: search first, then analyze results. Your agent decides which tools to call and in what exact order based on intermediate outputs.

Aggregating Job Data using LangChain

Need a bulk view of historical openings? The `get_historic_joas` tool retrieves paginated data for past job postings. Because your agent manages the state, it handles the continuation token automatically, ensuring you pull all records without manual intervention. This means you don't just get one page; you get a complete dataset of historic opportunities, which is critical when building complex reports in your LangChain application.

Validating Filters with the MCP Server

Before searching for jobs, your agent can use `get_code_list` to pull valid codes and values. This prevents bad data from messing up a search query. It's like checking all the allowed filter options before you write the final API call. This initial validation step keeps your entire LangChain pipeline clean, ensuring that when your agent calls `search_jobs`, it uses parameters that actually work with USAJOBS (OPM) data.

Setup guide

Set up USAJOBS (OPM) 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 USAJOBS (OPM) 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({
    "usajobs-opm-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 USAJOBS (OPM) 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 USAJOBS. 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 USAJOBS (OPM) 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 USAJOBS (OPM) MCP in LangChain

You call the client's `get_tools()` method and pass those tools to your ReAct agent. The agent then handles deciding which tool, like `search_jobs`, is necessary for the user query.

Yes. When you use tools that support continuation tokens, like `get_historic_joas`, your agent manages the state and calls the tool repeatedly until all available data is gathered.

Absolutely. Since the output of every MCP tool call is just another piece of data, you can feed that data into vector stores or other databases within your larger LangChain application.

This server touches job announcement text, historic job opening records, and filtering code lists. These are all public-facing details about federal employment opportunities.

LangChain helps by letting your agent break the query into small, actionable steps. It might call `get_code_list` first, then use that output to correctly structure a request to `search_jobs`.

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