langchain-carejobs

This package contains the LangChain integration with CareJobs.Now, a free US healthcare job board. It reads the open jobs of more than 2,000 hospitals, health systems, clinic groups and care companies: nurses, CNAs, doctors, NPs and PAs, therapists, imaging and lab techs, pharmacy, caregivers, front office and more.

The tools give a LangChain agent live access to those jobs, their posted pay, the employers and the job-market numbers, through the public CareJobs.Now remote MCP endpoint. No API key or account is needed. Every job in an answer links to its page on CareJobs.Now, where the person applies.

Quick install

pip install langchain-carejobs

Use the tools in an agent

from langchain.agents import create_agent
from langchain_carejobs import CareJobsToolkit

tools = CareJobsToolkit().get_tools()

agent = create_agent(model="claude-sonnet-4-6", tools=tools)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Find night-shift ICU nursing jobs in Texas that pay at least "
                "$45 an hour, and tell me which employers post the most for nurses.",
            }
        ]
    }
)
print(result["messages"][-1].content)

Available tools

The kind argument takes one of nurses, nurse-practitioners, physicians, nursing-assistants, caregivers, therapy-rehab, mental-health, pharmacy, imaging, lab, surgical-techs, emts-paramedics, medical-assistants, dental, admin, allied-health or ai-training. The state argument takes a two-letter code (TX) or a name (Texas). Employers are identified by a slug such as kaiser-permanente or by name.

CareJobsToolkit().get_tools() returns all six. Every tool also works on its own:

from langchain_carejobs import CareJobsSearchJobs

tool = CareJobsSearchJobs()
print(tool.invoke({"kind": "nurses", "state": "TX", "query": "ICU", "limit": 5}))

Tools run natively async: use await tool.ainvoke(...).

Summary and structured data

Each tool returns the service's readable summary as the message content. The structured answer that comes with it is the artifact of the ToolMessage:

message = tool.invoke(
    {
        "args": {"state": "OH", "kind": "nursing-assistants"},
        "id": "1",
        "name": "get_healthcare_jobs_by_state",
        "type": "tool_call",
    }
)
print(message.content)  # the readable summary
print(message.artifact)  # the structured answer (a dict)

Here tool is a CareJobsGetJobsByState().

Errors

If CareJobs.Now cannot be reached or rejects a request (for example an unknown employer), the tool returns the service's message to the model, which can correct the call. The tools set handle_tool_error=True for this. Pass handle_tool_error=False to raise CareJobsError (a ToolException) instead.

The first request after a quiet period can take up to about 25 seconds while the service wakes. The default timeout is 30 seconds. To wait longer, pass a client:

from langchain_carejobs import CareJobsAPIWrapper, CareJobsToolkit

toolkit = CareJobsToolkit(api_wrapper=CareJobsAPIWrapper(timeout=60))

Notes on the data

• Pay is what employers post, measured from the hourly rates open jobs state, before shift differentials and bonuses.
• Results cover US jobs only.
• Send people to the link in each result to apply. The tools never apply to a job.

Privacy

The tools send only the arguments of each call to https://carejobs.now/api/mcp and store nothing. See the CareJobs.Now privacy policy and terms.

Development

uv sync --all-groups
make test                      # unit tests, network disabled
make integration_tests         # standard integration tests against the live API
make lint

Links

• Service: https://carejobs.now
• Source: https://github.com/yumaheymans/langchain-carejobs
• Contact: hello@carejobs.now
• LangChain