Bring Employee Directory
to Pydantic AI
Learn how to connect Hurma to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Hurma MCP Server?
Connect your Hurma instance to any AI agent and manage your HR operations through natural conversation.
What you can do
- Recruiting Pipeline — List all candidates, inspect profiles, create new candidate records, and track hiring progress
- Employee Directory — Browse all employees with department and position details
- Time-Off Management — Monitor out-of-office schedules and leave requests
- Department Structure — Browse organizational departments
- Position Management — List all job positions
- Onboarding Tracking — Monitor new hire checklists and progress
How it works
1. Subscribe to this server
2. Enter your Hurma domain name and API Key
3. Start managing HR from Claude, Cursor, or any MCP-compatible client
Who is this for?
- HR Teams — manage candidates, employees, and leave without switching to the dashboard
- Hiring Managers — track recruiting pipeline and review candidate profiles
- Team Leads — monitor team availability and time-off schedules
Built-in capabilities (12)
Create a new candidate
Create a new leave or absence request
Export overtime data
Get details for a specific candidate
Get details for a specific employee
Get employee vacation balance
List recruitment candidates
List custom field definitions
List all company departments
List all employees
List employees currently out of office
List recruitment stages
Why Pydantic AI?
Pydantic AI validates every Hurma tool response against typed schemas, catching data inconsistencies at build time. Connect 12 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 Hurma integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Hurma connection logic from agent behavior for testable, maintainable code
Hurma in Pydantic AI
Hurma and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Hurma 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 Hurma in Pydantic AI
The Hurma 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 12 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
Hurma for Pydantic AI
Every tool call from Pydantic AI to the Hurma MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I manage the recruiting pipeline through the AI agent?
Yes. Use list_candidates to see all candidates with status, get_candidate_details for full profiles, and create_candidate to add new applicants.
Can I monitor who is out of office today?
Yes. list_out_of_office retrieves all current and upcoming time-off entries. Use list_leave_requests for pending approvals and get_leave_balances for remaining vacation days.
Does Hurma require a custom domain in addition to the API Key?
Yes. Each Hurma account has a unique subdomain. Provide the domain name and API Key. Requests go to https://{domain}.hurma.work/api/v1 with a Bearer token.
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 Hurma MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai