Can I process a refund through the agent?

Yes! Use the `refund_chargedesk_payment` tool with the charge ID. You can also specify an optional amount for a partial refund. The agent will trigger the refund on the original gateway.

How do I see all payments from a specific customer?

Use the `get_customer_details` tool with the unique customer ID. Your agent will fetch the profile, which includes a list of all successful and failed charges.

Where do I find my ChargeDesk Secret Key?

Log in to your ChargeDesk account and go to **Account Settings -> API**. You can view and copy your Secret Key from there.

ChargeDesk MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: ChargeDesk
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ChargeDesk through the 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 ChargeDesk "
            "(8 tools)."
        ),
    )

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

Connect your ChargeDesk account to any AI agent and take full control of your billing and payment operations across Stripe, PayPal, Braintree, and more through natural conversation. Streamline customer support and financial management.

Pydantic AI validates every ChargeDesk tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through the 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.

What you can do

Unified Payment Oversight — List and retrieve details for charges across all connected payment gateways natively
Refund Management — Process full or partial refunds for specific charges securely
Customer Intelligence — Access and monitor customer profiles and their complete billing history flawlessly
Subscription Tracking — List and retrieve details for active and inactive customer subscriptions securely
Gateway Auditing — List all connected gateways and verify their operational status flawlessly
Notification Management — Access and review configured webhooks and account alerts directly within your workspace

The ChargeDesk MCP Server exposes 8 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 ChargeDesk to Pydantic AI via MCP

Follow these steps to integrate the ChargeDesk 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 8 tools from ChargeDesk with type-safe schemas

Why Use Pydantic AI with the ChargeDesk MCP Server

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

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

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

ChargeDesk + Pydantic AI Use Cases

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

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

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

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

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

ChargeDesk MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect ChargeDesk to Pydantic AI via MCP:

get_charge_details

Get detailed information for a specific charge

get_customer_details

Get detailed information for a specific customer

list_chargedesk_charges

List recent charges from all gateways

list_chargedesk_customers

List all customers in your account

list_chargedesk_subscriptions

List active and inactive subscriptions

list_chargedesk_webhooks

List configured webhooks

list_connected_gateways

List all connected payment gateways

refund_chargedesk_payment

Refund a specific charge

Example Prompts for ChargeDesk in Pydantic AI

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

"Show me the last 10 charges in ChargeDesk."

"Refund $25.00 for charge ID 'ch_123456'."

"List all my connected payment gateways."

Troubleshooting ChargeDesk MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

ChargeDesk + Pydantic AI FAQ

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