How to Use the Dada Now Delivery MCP in Pydantic AI

Q: Can I use Pydantic AI to submit a complaint for a Dada Now Delivery order?

Yes, your agent would use the addcomplaint tool. Pydantic AI ensures that the complaint details you provide are correctly structured before the request is even sent to the server.

Q: What's the benefit of using Pydantic AI to re-add a failed Dada Now Delivery order?

When your agent uses the readdorder tool, Pydantic AI validates the response. This gives you absolute certainty that the order was successfully resubmitted and provides the new order details in a clean, typed object.

Q: Can I build a multi-step workflow, like estimating a fee then placing an order?

Definitely. Your agent calls queryorderfee and gets a validated Pydantic object back. You can then reliably extract the fee, get user confirmation, and proceed to call the addorder tool.

Build rock-solid delivery automations with Pydantic AI and Dada Now. Get type-safe, validated responses for every single API call.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dada Now Delivery MCP to Pydantic AI

Create your Vinkius account to connect Dada Now Delivery 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 Dada Now Delivery with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Error-Proof Your Delivery Operations

Your agent uses `add_order` to create a delivery. Pydantic AI doesn't just pass the JSON response back; it parses it into a Pydantic model. You get a typed object with the order ID and status, guaranteed. Here's the real value. If Dada Now's API returns an unexpected field from `query_order_status`, your agent won't crash or make up a status. It will raise a `ValidationError` immediately. You'll know exactly what went wrong, and where.

Manage Costs and Locations with Confidence

When your agent calls `query_order_fee`, it's not getting a string back. Pydantic AI converts the response into a structured model with typed fields for `currency` and `amount`. This eliminates a whole class of bugs in your cost calculation code. It works for inputs, too. The data you structure to `add_shop` or `update_shop` is validated against your Pydantic models on the way in. This ensures you never send malformed data to the Dada Now API, preventing silent failures.

A Correctness-First Dada Now MCP Server

This MCP server provides ten tools for working with the Dada Now API. Pydantic AI turns each one—from `add_tip` to `cancel_order`—into a typed function call for your agent. You know the inputs are correct, and you can trust the outputs. Because Pydantic AI is model-agnostic, you have options. You can start with a GPT-4-based agent and switch to a local Llama model later. Your tool logic doesn't change because the validation layer is independent of the LLM.

Setup guide

Set up Dada Now Delivery 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": {
        "dada-now-delivery-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Dada Now Delivery 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 Dada Now. 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 Dada Now Delivery 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 Dada Now Delivery MCP in Pydantic AI

Pydantic AI validates every API response from the MCP server against a strict Pydantic model. If data from a tool like `query_order_status` doesn't match the expected structure, your code gets a validation error, not corrupted data.

Yes, your agent would use the `add_complaint` tool. Pydantic AI ensures that the complaint details you provide are correctly structured before the request is even sent to the server.

When your agent uses the `readd_order` tool, Pydantic AI validates the response. This gives you absolute certainty that the order was successfully resubmitted and provides the new order details in a clean, typed object.

Definitely. Your agent calls `query_order_fee` and gets a validated Pydantic object back. You can then reliably extract the fee, get user confirmation, and proceed to call the `add_order` tool.

The server processes your delivery details, including order contents and addresses. All traffic between your Pydantic AI agent and the Vinkius MCP server is encrypted. Vinkius's zero-trust design means each tool call runs in a fresh sandbox that is immediately torn down, leaving no trace of your order 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