How to Use the Workable MCP in AutoGen

Q: Can I use Workable and AutoGen to vet a hiring plan?

Yes. You can set up an agent team where one reviews listjobs and another checks against listaccountmembers, forcing them to debate the feasibility of the current staffing plan.

Q: If I need to check linked accounts with Workable and AutoGen, how does it work?

You'll have one agent calling listlinkedaccounts and another challenging the scope of those connections. The final output is a deliberative summary that pinpoints exactly what needs attention.

Get consensus on hiring strategy using AutoGen.

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 AutoGen

Create your Vinkius account to connect Workable to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Candidate Eligibility with MCP Server

You can set up an agent to run `list_all_candidates` and feed the results into a debate. One agent might argue for seniority based on `get_candidate_profile`, while another might challenge that by pointing out a lack of specific job experience. The agents don't just report; they negotiate. They argue until the group converges on an agreed-upon decision regarding candidate readiness.

Consensus on Job Openings using MCP Server

Have a debate between two agents about which roles need filling. One calls `list_jobs` to see all openings, and the other uses that list to determine priority based on linked accounts. They challenge each other's assumptions. The final output isn't just data; it's a consensus recommendation that requires multiple perspectives to achieve.

Reviewing Team Structure with AutoGen

You can assign one agent the role of 'HR Specialist' and another the role of 'Budget Analyst.' The HR specialist calls `list_account_members`, and the Budget Analyst challenges that list by checking for redundant roles or excessive staffing. The system generates a finalized report, incorporating both structural data (`list_linked_accounts`) and critical business constraints.

Setup guide

Set up Workable MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Workable tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Workable_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Workable data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Workable_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Workable data")
    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 AutoGen

You define multiple agents with specific roles. These agents then take turns calling the MCP Server tools—like `get_job_details`—and discussing the results until they reach consensus.

The servers provide structured data like job details, candidate profiles, and member lists. These inputs form the basis of the debate, allowing agents to challenge assumptions based on real API figures.

Yes. You can set up an agent team where one reviews `list_jobs` and another checks against `list_account_members`, forcing them to debate the feasibility of the current staffing plan.

Yes. The framework supports various transports, allowing agents to manage multiple tool calls concurrently and synthesize a final conclusion based on all inputs.

You'll have one agent calling `list_linked_accounts` and another challenging the scope of those connections. The final output is a deliberative summary that pinpoints exactly what needs attention.

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