How to Use the ChargeDesk MCP in Pydantic AI

Q: How do I install ChargeDesk for Pydantic AI?

Run pip install "pydantic-ai-slimmcp" to get the required dependencies. Initialize an MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset array into your Agent constructor.

Q: Is MCPServerHTTP supported for ChargeDesk in Pydantic AI?

No, MCPServerHTTP is deprecated in current versions. You must use the unified MCPToolset class configured with your HTTP URL. This handles both Streamable HTTP and SSE transports correctly.

Build type-safe billing agents with Pydantic AI that validate every ChargeDesk transaction against strict schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChargeDesk MCP to Pydantic AI

Create your Vinkius account to connect ChargeDesk 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 ChargeDesk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Refunds in Pydantic AI

Trigger accurate payment reversals using the `refund_chargedesk_payment` tool. Pydantic AI enforces strict type checking on the refund parameters before the request even hits the network. If the agent tries to pass a string instead of a float for the amount, the framework throws a loud validation error immediately. Reviewing past transactions requires the same rigor. Agents call `list_chargedesk_charges` to pull recent payments from all connected gateways. This MCP integration parses the incoming JSON against your predefined Pydantic models, guaranteeing that fields like currency codes and timestamps are formatted correctly.

Parse Subscriptions via MCP Server

Retrieve recurring billing states with the `list_chargedesk_subscriptions` tool. Your Python application ingests the active and inactive subscription data and validates the nested gateway responses. Silent data corruption is impossible because the agent crashes if the API returns unexpected null values. Resolving webhook configurations works exactly the same way. You run `list_chargedesk_webhooks` to audit your event endpoints. The agent verifies that every webhook URL matches your expected regex pattern, ensuring your infrastructure is actually receiving payment failure notifications.

Extract Verified Customer Records

Fetch specific user billing profiles by calling `get_customer_details`. The agent requests the profile and Pydantic AI guarantees the returned email addresses and account IDs meet your schema requirements. You swap between Anthropic, OpenAI, or local models without rewriting this validation logic. Broad account audits rely on `list_chargedesk_customers`. The agent paginates through your entire user base to calculate total revenue metrics. Because every record passes through Pydantic's runtime checks, your downstream reporting tools never ingest malformed billing data.

Setup guide

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

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

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

Run `pip install "pydantic-ai-slim[mcp]"` to get the required dependencies. Initialize an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset array into your Agent constructor.

The framework is designed to fail loudly if the LLM hallucinates a parameter or the API returns a malformed response. If a tool requires a specific transaction ID format and the agent guesses it, Pydantic throws a validation error. This prevents invalid API calls from executing.

Yes, the framework is entirely model-agnostic. You configure the agent to use a local Ollama instance and it will still execute the exact same tool calls. The validation layer operates independently of the LLM provider.

No, `MCPServerHTTP` is deprecated in current versions. You must use the unified `MCPToolset` class configured with your HTTP URL. This handles both Streamable HTTP and SSE transports correctly.

Nobody besides your authenticated client. The MCP server runs in an isolated V8 sandbox that drops all memory state the moment the API returns the customer record. We manage the connection but never persist your data.

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