How to Use the Manatal MCP in Pydantic AI

Q: Is the Manatal MCP server setup difficult in Pydantic AI?

You just point the MCPToolset to your server URL. The framework handles the rest of the integration, allowing you to focus on your agent's logic.

Strictly type-safe Manatal integration for Pydantic AI. Validate every candidate and job response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Manatal MCP to Pydantic AI

Create your Vinkius account to connect Manatal 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 Manatal with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe candidate lookups in Pydantic AI

Your agent calls `get_candidate` and `list_candidates` with guaranteed schema validation. If the ATS returns unexpected fields, your agent fails immediately. This prevents silent data corruption. You know exactly what data your agent is working with at every step of the recruitment process.

Reliable job and application data

Fetch current openings with `list_jobs` and `get_job` while enforcing strict model structures. Your agent rejects malformed responses before they cause issues. This setup ensures your agent always has high-quality data. It keeps your hiring pipeline running without unexpected runtime errors.

Mapping organizations in Pydantic AI

Retrieve your company structure with `list_organizations` and `list_departments`. The server provides the data, and your Pydantic models enforce the structure. Your agent gets a clear view of your business hierarchy. It uses this valid data to route candidates to the correct internal teams.

Setup guide

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

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

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

Define your Pydantic models for candidates and jobs. The toolset validates the server's output against these models automatically during every tool execution.

Pydantic AI catches the schema mismatch during runtime. You get a descriptive validation error instead of passing bad data to your agent.

Yes. The server is model-agnostic. You can pair it with local models or cloud-hosted ones while keeping your strict type-safety guarantees.

You just point the `MCPToolset` to your server URL. The framework handles the rest of the integration, allowing you to focus on your agent's logic.

Your data is validated in memory at the moment of receipt. No persistence occurs on the server, and your Pydantic models ensure only authorized data fields are processed.

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