How to Use the Giftpack MCP in Pydantic AI

Q: Does Giftpack support runtime validation for campaign statistics in Pydantic AI?

Yes, when calling getcampaignstatistics, the returned analytics payload is validated against your Pydantic schemas. This guarantees your reporting agent never processes corrupted metrics.

Q: How does Pydantic AI handle catalog searches with Giftpack?

Your agent calls searchgiftcatalog to find items matching the recipient's region. The response is parsed into typed models so your agent can safely decide which product to select.

Q: Can my agent trigger a physical gift send automatically?

Yes, the agent calls triggergiftsend once it selects an item. This dispatches the physical gift directly to the verified recipient.

Automate your corporate gifting with Pydantic AI to guarantee type-safe recipient validation and zero runtime errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Giftpack MCP to Pydantic AI

Create your Vinkius account to connect Giftpack 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 Giftpack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe recipient ingestion in Pydantic AI

The `create_recipient` tool enforces strict data validation when adding new contacts to your Pydantic AI agent. If a phone number or email is malformed, the framework raises a validation error immediately rather than sending corrupt data to the shipping API. You can then use `get_recipient_details` to verify the parsed contact object. This keeps your shipping database clean and prevents failed physical deliveries due to typos.

Safe campaign creation using Pydantic AI MCP Server

The `create_campaign` tool requires strict schema validation before your Pydantic AI agent can spin up a new corporate gifting run. This ensures that budget limits and campaign titles always match your exact database types. Your agent can safely query `list_gifting_campaigns` to verify existing campaign IDs. This prevents runtime crashes when matching recipients to active corporate budgets.

Validated order fulfillment and tracking

The `get_order_fulfillment_status` tool parses shipping updates into strict Python classes within your Pydantic AI environment. Your agent reads the structured tracking payload without risking silent errors from unexpected API format changes. If you need to audit past shipments, `list_gift_orders` returns a validated list of recent orders. This integration ensures your financial reporting scripts always receive clean, typed data.

Setup guide

Set up Giftpack 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": {
        "giftpack-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the MCPToolset class with your Vinkius HTTP endpoint URL. Pass the toolset object directly into the Agent constructor to expose the gifting tools.

Yes, when calling `get_campaign_statistics`, the returned analytics payload is validated against your Pydantic schemas. This guarantees your reporting agent never processes corrupted metrics.

Your agent calls `search_gift_catalog` to find items matching the recipient's region. The response is parsed into typed models so your agent can safely decide which product to select.

Yes, the agent calls `trigger_gift_send` once it selects an item. This dispatches the physical gift directly to the verified recipient.

All recipient details and order IDs are processed through ephemeral V8 isolates. No customer data is stored on Vinkius servers, and all API calls are signed using single-token authentication to block unauthorized access.

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