How to Use the WebHR MCP in Pydantic AI

Q: How do I verify employee details using WebHR and Pydantic AI?

You call getemployeedetails through the agent. Because of Pydantic validation, you're guaranteed that the fields returned—like ID or name—are in the exact format your program expects.

Q: Can I pull department lists and job data with WebHR using Pydantic AI?

Yes. You get listcompanydepartments for organizational structure, and you can pair that with listjobpostings. The type-safety ensures the results from both tools fit together correctly in your application logic.

Q: What leave data is provided by WebHR when using Pydantic AI?

The server provides two key lists: listavailableleavetypes for policy, and listleaverequests for history. Both tool outputs are validated against strict models, so the data integrity is high.

Q: If I check attendance logs, how does WebHR work with Pydantic AI?

You call listattendancelogs. The agent uses Pydantic to validate that every entry has a start time, end time, and associated employee ID in the correct format. No guesswork.

Q: Does WebHR support listing job candidates with Pydantic AI?

Yes. You can list applicants using listjobcandidates. The framework validates that each candidate record contains all necessary, expected fields—preventing issues from incomplete API responses.

Ensure data correctness with Pydantic AI and WebHR.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WebHR MCP to Pydantic AI

Create your Vinkius account to connect WebHR 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 WebHR with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get validated attendance summaries.

The agent calls `get_attendance_summary` to pull aggregated metrics. Crucially, the response is automatically validated against a schema model before your code sees it. If the API returns bad or unexpected data, Pydantic AI fails loudly with an error—you never get silent corruption.

Check employee records and organizational structure.

Need to know who someone is? Use `get_employee_details`. Every piece of returned information (name, ID, title) must match the defined Pydantic schema. It also validates structural data; calling `list_company_departments` ensures that every department name and type you receive adheres to your expected format.

Manage job listings with high accuracy.

Agents use `list_job_postings` to pull open roles, but the result is typed. This means you know exactly which fields are present and what data type they hold. This reliability extends to tracking applications via `list_job_candidates`. You can trust that every job record or candidate entry meets your required structure.

Setup guide

Set up WebHR 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": {
        "webhr-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent WebHR 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 WebHR. 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 WebHR 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 WebHR MCP in Pydantic AI

You call `get_employee_details` through the agent. Because of Pydantic validation, you're guaranteed that the fields returned—like ID or name—are in the exact format your program expects.

Yes. You get `list_company_departments` for organizational structure, and you can pair that with `list_job_postings`. The type-safety ensures the results from both tools fit together correctly in your application logic.

The server provides two key lists: `list_available_leave_types` for policy, and `list_leave_requests` for history. Both tool outputs are validated against strict models, so the data integrity is high.

You call `list_attendance_logs`. The agent uses Pydantic to validate that every entry has a start time, end time, and associated employee ID in the correct format. No guesswork.

Yes. You can list applicants using `list_job_candidates`. The framework validates that each candidate record contains all necessary, expected fields—preventing issues from incomplete API responses.

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