How to Use the HRBlade MCP in Pydantic AI

Q: How do I add HRBlade to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize MCPToolset with your Vinkius HTTP URL and assign it to the toolsets array on your Agent.

Q: Do I still use MCPServerHTTP?

No. That class is deprecated. You use the unified MCPToolset which natively handles both SSE and Streamable HTTP transports.

Strictly validate HRBlade data in your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HRBlade MCP to Pydantic AI

Create your Vinkius account to connect HRBlade 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 HRBlade with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe candidate lookups

The `get_candidate_details` tool returns applicant information that Pydantic AI instantly validates against your predefined models. You connect the server by passing `MCPToolset` with your HTTP endpoint to the Agent constructor. When the agent calls `list_candidates`, the framework checks every field in the response. If the ATS returns a missing email or malformed ID, the system throws a hard validation error instead of hallucinating data.

Build templates without silent failures

Your agent uses `create_interview` to configure new screening questions via a JSON string. Because Pydantic enforces strict typing, you know exactly what parameters the model attempts to pass. To verify the setup, the agent runs `list_interviews`. The unified toolset approach ensures the response maps cleanly to your Python objects, regardless of whether you use OpenAI or a local model.

Expose the HRBlade MCP Server safely

The `send_interview_invitation` tool dispatches emails to applicants. Your agent constructs the JSON payload, and Pydantic AI guarantees the schema matches before the network request ever fires. After invites go out, the agent monitors `list_interview_responses` for completed video interviews. The framework handles the Streamable HTTP transport quietly in the background.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Initialize `MCPToolset` with your Vinkius HTTP URL and assign it to the `toolsets` array on your Agent.

You likely defined a strict schema that the ATS data does not perfectly match. If an applicant record lacks a field you marked as required, the framework throws a validation error by design.

No. That class is deprecated. You use the unified `MCPToolset` which natively handles both SSE and Streamable HTTP transports.

Yes. The framework is completely model-agnostic. You dictate the logic, and Pydantic enforces the data structure regardless of the underlying LLM.

Vinkius routes all applicant emails and phone numbers through an isolated, ephemeral execution environment. We manage the authentication layer, and the data flows straight to your local validation models without ever hitting disk.

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