How do I get my Argyle API Key ID and Secret?

Log in to the Argyle Dashboard, go to **Settings > API Keys**, and you can generate your Client ID and Client Secret there.

What is the Argyle Link flow?

Argyle Link is an embedded UI component where your users log in to their payroll providers. Once they connect, you can use their User ID with this server to retrieve their data.

Can I use this server for testing in Sandbox?

Yes, configure the `ARGYLE_SANDBOX` environment variable to `true` to connect to the Argyle Sandbox environment (`api-sandbox.argyle.com`).

Argyle MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Argyle
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Argyle through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Argyle "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Argyle?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Argyle MCP Server

The Argyle MCP Server brings automated employment and income verification directly to your AI agent. Seamlessly manage your user verification workflows, retrieve detailed employment history, and monitor income totals using simple natural language.

Pydantic AI validates every Argyle tool response against typed schemas, catching data inconsistencies at build time. Connect 7 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.

Key Capabilities

User Management — List all users in your Argyle account and create new unique user IDs for verification flows.
Employment Verification — Retrieve verified employment status, hire dates, job titles, and employer details from the source.
Income Analysis — Access detailed income totals and breakdown, including YTD, monthly, and per-pay-period data.
Payout Tracking — List individual pay period details (payouts) to understand gross/net pay and deductions.
Verified Identities — Retrieve verified name, address, and contact information directly from payroll sources.
Secure Data Access — Uses secure API keys and supports sandbox mode for safe testing and production usage.

The Argyle MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Argyle to Pydantic AI via MCP

Follow these steps to integrate the Argyle MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Argyle with type-safe schemas

Why Use Pydantic AI with the Argyle MCP Server

Pydantic AI provides unique advantages when paired with Argyle through the Model Context Protocol.

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 Argyle integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Argyle connection logic from agent behavior for testable, maintainable code

Argyle + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Argyle MCP Server delivers measurable value.

Type-safe data pipelines: query Argyle with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Argyle tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Argyle and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Argyle responses and write comprehensive agent tests

Argyle MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Argyle to Pydantic AI via MCP:

create_user

Create a new user in Argyle

get_account_check

Verify Argyle account connection

get_employment

Retrieve employment history for a specific user

get_income

Retrieve income totals and breakdown for a user

list_identities

Retrieve verified identity information for a user

list_payouts

List individual pay period details (payouts) for a user

list_users

List all users created in your Argyle account

Example Prompts for Argyle in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Argyle immediately.

"List all users in my Argyle account."

"Show me the employment history for user 'user_12345'."

"What is the total YTD income for user 'user_abc'?"

Troubleshooting Argyle MCP Server with Pydantic AI

Common issues when connecting Argyle to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Argyle + Pydantic AI FAQ

Common questions about integrating Argyle MCP Server with Pydantic AI.

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 Argyle MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.