Bring Applicant Tracking
to Pydantic AI
Learn how to connect Workable to Pydantic AI and start using 7 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Workable MCP Server?
Connect your Workable recruiting account to any AI agent and simplify how you manage your hiring pipelines, track candidates, and coordinate with your team through natural conversation.
What you can do
- Job Management — List all active and archived job openings and retrieve detailed job descriptions and requirements.
- Candidate Tracking — List and inspect candidates across all jobs, and drill down into specific profiles for experience and status.
- Direct Sourcing — Programmatically register new candidates to specific job openings to accelerate your hiring process.
- Team Coordination — List account members and recruiters to understand your hiring team structure.
- Ecosystem Overview — List linked accounts and verify your Workable instance configuration via AI.
How it works
1. Subscribe to this server
2. Enter your Workable Subdomain and API Key
3. Start managing your recruitment machine from Claude, Cursor, or any MCP client
Who is this for?
- Recruiters & HR Managers — quickly check candidate statuses and job metadata via simple AI queries.
- Hiring Managers — monitor the progress of specific pipelines and review new applicants without opening the dashboard.
- Operations Teams — automate candidate registration and track team activity levels directly from the workspace.
Built-in capabilities (7)
Register a new candidate to a job
Get details for a specific candidate
Get details for a specific job
List hiring team members
List candidates across all jobs
List active job openings
List connected accounts
Why Pydantic AI?
Pydantic AI validates every Workable tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Workable integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Workable connection logic from agent behavior for testable, maintainable code
Workable in Pydantic AI
Workable and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Workable to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Workable in Pydantic AI
The Workable MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 7 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Workable for Pydantic AI
Every tool call from Pydantic AI to the Workable MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find the shortcode for a specific job?
Use the list_jobs tool. It returns a list of all your openings, each with its unique shortcode required for more detailed queries or actions.
Can I add a new candidate directly to a job via AI?
Yes! Use the create_candidate action. Provide the job shortcode along with the candidate's name and email to register them in your Workable pipeline.
Is it possible to see the recruiter assigned to an account?
Absolutely. Run the list_account_members query to retrieve the directory of all users and recruiters in your instance, including their roles.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Workable MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai