How to Use the Workable MCP in Pydantic AI

Q: How do I list active jobs using Workable and Pydantic AI?

You call listjobs. The agent processes this tool output, and Pydantic validates the results instantly. If the API returns bad data, your agent fails loudly instead of silently corrupting its state.

Q: Does Pydantic AI guarantee correct candidate profile retrieval from Workable?

Yes. When you use getcandidateprofile, the framework validates every returned field against your schema. You never have to worry about hallucinated or unexpected data types.

Q: What does Pydantic AI do when I list all candidates from Workable?

It processes listallcandidates. This means that even if the underlying API is messy, your agent receives a clean Python object whose structure you know for certain.

Q: Can Pydantic AI help me manage linked accounts in Workable?

You use listlinkedaccounts. The type validation ensures that the IDs and names returned are structured correctly, making it safe for your agent to act on this data.

Write reliable, type-safe agents with Pydantic AI and Workable.

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 Pydantic AI

Create your Vinkius account to connect Workable to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structuring candidate records using MCP Server tools.

When your agent finds a top prospect, it calls `create_candidate`. Because you're running this on Pydantic AI, the resulting data is validated against strict schemas at runtime. No unexpected fields allowed. It also uses `get_job_details` to ensure that any new candidate record is correctly linked to an existing job opening.

Retrieving structured lists with Pydantic AI.

`list_jobs` provides a list of active jobs, and Pydantic ensures the output adheres to your expected schema. This prevents silent failures when your agent expects specific fields. You can get an overview of everyone by running `list_all_candidates`. The type-safe framework guarantees that every returned candidate object has the right structure.

Auditing accounts and team members via MCP Server.

`list_account_members` pulls a list of people, validating each entry against your model. This lets your agent know exactly who is on the hiring team without runtime surprises. To scope out where you're working, use `list_linked_accounts`. Pydantic ensures that every account ID returned matches what your type definitions expect.

Setup guide

Set up Workable MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "workable-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Workable tools.",
)

result = await agent.run("List recent Workable transactions")
print(result.output)

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 Pydantic AI

You call `list_jobs`. The agent processes this tool output, and Pydantic validates the results instantly. If the API returns bad data, your agent fails loudly instead of silently corrupting its state.

Yes. When you use `get_candidate_profile`, the framework validates every returned field against your schema. You never have to worry about hallucinated or unexpected data types.

It processes `list_all_candidates`. This means that even if the underlying API is messy, your agent receives a clean Python object whose structure you know for certain.

You use `list_linked_accounts`. The type validation ensures that the IDs and names returned are structured correctly, making it safe for your agent to act on this data.

The server manages job details and candidate records. The primary benefit of using Pydantic is that the resulting structured data, whether a single profile or a list, is always correct.

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