How to Use the Troops MCP in Pydantic AI

Q: How does Pydantic AI handle candidate registration with Troops?

Your agent uses createcandidate. Because of the framework, if the API sends incomplete or malformed data for a new candidate, your Python code fails immediately and tells you exactly what's wrong.

Q: Can I list job offers reliably using Troops and Pydantic AI?

Yes. The listjobs tool ensures that the returned job data adheres to your schema, even if the underlying HR system changes its output format. You get predictable results every time.

Q: What about processing timesheets and contracts with Troops and Pydantic AI?

You can chain submittimesheet and generatecontract. The strength here is that the data moving between these tools is always validated, making complex HR workflows safe.

Q: Does this MCP Server support multiple job statuses?

Yep. You use listjobs, which lets you filter by status. This functionality allows your agent to pull specific subsets of data needed for different reports or processes.

Build type-safe HR automation with Pydantic AI's MCP Server integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Troops MCP to Pydantic AI

Create your Vinkius account to connect Troops 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 Troops with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validating Candidate Data in the Pydantic AI Agent

The agent registers new people using `create_candidate` and pulls details via `get_candidate`. If the underlying API returns unexpected field names, your system fails loudly with a validation error—no silent corruption. The guarantee here is correctness. Every piece of candidate data passed through this MCP Server must conform to your defined Pydantic schema.

Managing Job Offers via the MCP Server

You can define a new role with `create_job`. You also run `list_jobs` to see current openings, filtering by status. The framework ensures that job records are always structured correctly. This means your agent doesn't guess at data formats; it relies on strict, validated Python types.

Securely Processing HR Documents

The workflow covers hours and paperwork. Use `submit_timesheet` for time records, then use `generate_contract`. The type-safe nature means the contract data structure is guaranteed when your agent calls `sign_contract`. It's about preventing bad inputs from causing expensive operational mistakes.

Setup guide

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

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

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

Your agent uses `create_candidate`. Because of the framework, if the API sends incomplete or malformed data for a new candidate, your Python code fails immediately and tells you exactly what's wrong.

Yes. The `list_jobs` tool ensures that the returned job data adheres to your schema, even if the underlying HR system changes its output format. You get predictable results every time.

You can chain `submit_timesheet` and `generate_contract`. The strength here is that the data moving between these tools is always validated, making complex HR workflows safe.

Yep. You use `list_jobs`, which lets you filter by status. This functionality allows your agent to pull specific subsets of data needed for different reports or processes.

The MCP Server touches Candidate Data. The Pydantic AI framework adds a layer of safety by ensuring that even if the data source is messy, your agent only receives and processes fields that match your strict Python models.

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