How do I obtain a Finch Access Token?

Access tokens are generated when a user successfully completes the Finch Connect authorization flow for their specific HRIS or payroll provider.

Which HRIS providers does Finch support?

Finch supports over 200 providers including Gusto, ADP, Workday, BambooHR, and Rippling. You can use the `list_supported_providers` tool to see the full list flawlessy.

Can I see individual pay statements?

Yes! The `list_pay_statements` tool allows you to retrieve payment details for individuals if the connected organization has granted the necessary payroll permissions flawlessy.

Finch MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Finch
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Finch 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 Finch "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Finch?"
    )
    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 Finch MCP Server

Finch is the unified API for HRIS and payroll. This MCP server allows your AI agent to interact with various HR and payroll providers through a single integration flawlessly.

Pydantic AI validates every Finch tool response against typed schemas, catching data inconsistencies at build time. Connect 11 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 Features

Directory Orchestration — List all employees in the connected organization and fetch detailed profiles natively.
Employment Intelligence — Retrieve granular employment data including job titles, departments, and compensation flawlessly.
Payroll Transparency — Access pay groups and individual pay statements to monitor payroll data synchronously.
Connection Introspection — Check the status, provider, and authorized permissions for any connection flawlessly native.
Automated Job Tracking — Monitor data sync jobs to ensure your HRIS data is always up to date flawlessly through the agent.
Provider Discovery — List all supported HRIS and payroll providers to verify integration compatibility flawlessly.

The Finch MCP Server exposes 11 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 Finch to Pydantic AI via MCP

Follow these steps to integrate the Finch 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 11 tools from Finch with type-safe schemas

Why Use Pydantic AI with the Finch MCP Server

Pydantic AI provides unique advantages when paired with Finch 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 Finch integration code

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

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

Finch + Pydantic AI Use Cases

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

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

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

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

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

Finch MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Finch to Pydantic AI via MCP:

get_automated_job

Get details for a specific automated job

get_company

Get organization data (legal name, EIN, primary address)

get_employment

Get employment data for an individual (title, salary, department, etc.)

get_individual

Get personal data for an individual (name, email, SSN, etc.)

get_me

Get details for the authorized application/user connection

introspect

Check the status and permissions of the current connection

list_automated_jobs

List automated data sync jobs

list_directory

Read the employee directory for the connected organization

list_pay_groups

List pay groups for the organization

list_pay_statements

List pay statements for a specific payment ID

list_supported_providers

List all HRIS/Payroll providers supported by Finch

Example Prompts for Finch in Pydantic AI

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

"List all employees in the directory."

"Check the status of my connection to Gusto."

"List pay statements for payment ID pmt_123."

Troubleshooting Finch MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Finch + Pydantic AI FAQ

Common questions about integrating Finch 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 Finch MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.