How to Use the Sharpei MCP in Pydantic AI

Q: How does Sharpei work with Pydantic AI for recurring payment logic?

When your agent uses getsubscription, the response is validated against a schema. If any field is missing or malformed, the agent fails loud and clear, preventing bad data from entering your system.

Q: Does Sharpei provide full visibility into active store apps using Pydantic AI?

Yes. The listapplications tool provides a structured list of all applications. Your agent can process this type-safe data reliably for auditing purposes.

Q: What if I need document details while using Sharpei and Pydantic AI?

You use getdocument. The response is strictly typed, meaning you receive the exact fields you need—like metadata or file IDs—without worrying about corruption.

Q: Can I list all webhooks using Sharpei and Pydantic AI?

The listwebhooks tool gives you a guaranteed structure for every webhook record. This makes it easy to build type-safe checks into your deployment pipeline.

Q: If I need to check data privacy when using Sharpei and Pydantic AI, what specific information is exposed?

This MCP Server touches application documents. Using getapplication allows you to validate the scope of access by retrieving structured details about each connected app.

Type-safe, reliable e-commerce data for Pydantic AI. Guaranteed correct responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sharpei MCP to Pydantic AI

Create your Vinkius account to connect Sharpei to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sharpei with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Fetch Subscription State

`get_subscription` returns subscription details validated against a schema. When your agent calls this, it gets precise payment and billing information—no unexpected fields allowed. This guarantees the data is correct. You can list all plans using `list_subscriptions`. The structured output means your code doesn't have to guess what kind of data it's receiving.

Manage App Lifecycle

`create_application` handles the setup and uses strict typing for required parameters. This makes building new integrations predictable. After creation, `get_application` confirms the details using a validated Pydantic model. To keep tabs on everything, use `list_applications`. The structured list lets your agent process data reliably without runtime errors.

Audit Store Connections

`list_webhooks` provides a guaranteed schema for all active webhooks. This means when your Pydantic AI client reads it, the structure is exactly what you expect. You can also use `get_documents` to list documents associated with an application. The strict validation ensures that whatever data type comes back—like document metadata—is usable right away.

Setup guide

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

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

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

When your agent uses `get_subscription`, the response is validated against a schema. If any field is missing or malformed, the agent fails loud and clear, preventing bad data from entering your system.

Yes. The `list_applications` tool provides a structured list of all applications. Your agent can process this type-safe data reliably for auditing purposes.

You use `get_document`. The response is strictly typed, meaning you receive the exact fields you need—like metadata or file IDs—without worrying about corruption.

The `list_webhooks` tool gives you a guaranteed structure for every webhook record. This makes it easy to build type-safe checks into your deployment pipeline.

This MCP Server touches application documents. Using `get_application` allows you to validate the scope of access by retrieving structured details about each connected app.

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