How to Use the Workable MCP in LangChain

Q: Can I pull team member data using Workable and LangChain?

Yes. You use listaccountmembers to get all current employees, which you can then pass into another tool call to see what jobs they're currently involved with.

Build multi-step recruitment pipelines with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Workable MCP to LangChain

Create your Vinkius account to connect Workable 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 Workable with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining Candidate Data Retrieval with MCP Server

You can start by calling `list_jobs` to see all open roles. Then, you'll take a job ID from that output and pass it directly into `get_job_details`. This sequence lets your agent build a complete view of the opportunity right down the line. This pattern means your AI client doesn't just run tools; it reasons. The output of one function call—like getting a specific Job ID—becomes the necessary input for the next, creating complex workflows.

Managing Team Structure and Candidates via MCP Server

Need to know who's on the hiring team? Use `list_account_members` first. Once you have a member ID, you can use that specific ID to check which roles they manage by calling `get_candidate_profile`. It’s about linking people and processes together. This capability lets your agent execute logic like: 'Find all members who are involved in Job X, then list their top candidates.' The chain keeps the context flowing.

Building Full Candidate Lifecycles with LangChain

The `create_candidate` tool lets your agent register a new person to the system. After that, you can immediately call `get_candidate_profile` using the ID of the candidate you just created. This confirms the data entered and makes it available for further steps in your chain. Your LangChain application uses these tools sequentially—it's not random calls. It's a structured flow where the agent determines the exact order needed to hit a business goal.

Setup guide

Set up Workable 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 Workable 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({
    "workable-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 Workable 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 Workable. 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 Workable 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 Workable MCP in LangChain

You build complex reasoning pipelines. For example, your agent can first call `list_jobs` to identify open roles, then pass those job IDs into a subsequent tool that gets the specific requirements for each one.

The MCP Server exposes job details, candidate profiles, and account member lists. Your agent uses these structured outputs (like Job IDs or Candidate records) to guide its next set of tool calls.

Absolutely. The core design of your framework is chaining. You use the output of one `list_all_candidates` call, for instance, as a list to iterate over when calling other tools in the chain.

Yes. You use `list_account_members` to get all current employees, which you can then pass into another tool call to see what jobs they're currently involved with.

It supports stateless execution by default. However, your client setup allows you to use a session context, letting your agent remember IDs or filtered lists across multiple tool calls.

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