How to Use the Kelkoo MCP in Pydantic AI

Strictly type your Kelkoo retail data with Pydantic AI to ensure your agents never process malformed offer responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kelkoo MCP to Pydantic AI

Create your Vinkius account to connect Kelkoo 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 Kelkoo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe offer searching with Pydantic AI

Every response from `search_offers` is validated against your Pydantic models at runtime. If the API returns a bad field, the agent stops immediately. This catches issues before they hit your core logic. You define the schema, and the agent ensures the Kelkoo data matches your expectations perfectly.

Explore product hierarchies in Pydantic AI

Use `get_category_tree` to fetch the retail taxonomy. Your agent relies on Pydantic to ensure the category structure is parsed correctly every single time. This makes your category navigation robust. You don't have to worry about missing keys in the `list_categories` output because the framework handles the validation for you.

Validate merchant data in Pydantic AI

Run `list_merchants` and let your agent verify the merchant objects against your defined models. It keeps your agent's knowledge base clean and accurate. This approach is ideal for production apps where you can't afford silent failures. If the `list_merchants` output changes, your agent flags it immediately.

Setup guide

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

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

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

You define a Pydantic model for the tool response. When the agent calls `get_offer_details`, Pydantic AI validates the JSON payload against your model automatically.

Yes. The MCPToolset supports SSE transports, which is the best way to handle streaming responses from the Kelkoo server.

Your agent will trigger a validation error if the response doesn't match your Pydantic model. You'll know the exact field that failed.

The data is strictly for your agent's use. Vinkius secures the communication, and only you have the endpoint token to query the Kelkoo inventory.

You can run the MCP server as a local process and point the Pydantic AI toolset to it. It keeps your retail data traffic entirely within your environment.

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