How to Use the Azure Cosmos DB Container MCP in Pydantic AI

Q: How do I handle partition keys when deleting documents?

Pass the partition key directly to the deletedocument tool. The agent extracts this from your Pydantic model to ensure the delete operation targets the correct partition.

Run type-safe NoSQL operations in Pydantic AI with runtime validation using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Cosmos DB Container MCP to Pydantic AI

Create your Vinkius account to connect Azure Cosmos DB Container 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 Azure Cosmos DB Container with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Cosmos DB documents using Pydantic AI

This MCP Server integrates with Pydantic AI to enforce strict schemas on your NoSQL writes. When the agent calls `create_document`, the framework validates the payload against your Pydantic models before sending it to Azure. This setup eliminates silent database corruption. If the agent attempts to write a document with a missing partition key or invalid fields, the validation layer catches it instantly.

Parse Cosmos DB documents into typed Python models

The `get_document` tool retrieves JSON documents by ID and maps them directly to your defined Pydantic schemas. Your Pydantic AI agent receives fully typed objects instead of raw, unpredictable dictionaries. If the returned document structure deviates from your model, the system raises a validation error. You get absolute certainty that your application logic is working with clean, expected data.

Run schema-validated SQL queries with Pydantic AI

The `query_documents` tool lets your agent query your container using structured SQL. Pydantic AI validates the query parameters at runtime, ensuring the agent doesn't inject malformed SQL strings. The results are parsed back into list models automatically. This gives you a reliable pipeline where every single database record is type-checked before the agent processes it.

Setup guide

Set up Azure Cosmos DB Container 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": {
        "azure-cosmos-db-container-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Azure Cosmos DB Container 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 Azure Cosmos DB Container. 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 Azure Cosmos DB Container 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 Azure Cosmos DB Container MCP in Pydantic AI

Initialize the MCPToolset with your Vinkius HTTP endpoint URL. Pass this instance into the toolsets argument when constructing your Pydantic AI Agent.

The framework raises a validation error immediately, halting execution. This prevents your agent from processing corrupt or unexpected NoSQL schemas.

No, you must use the unified MCPToolset class. This is the modern, supported method for integrating external tools into your Pydantic AI workflows.

Pass the partition key directly to the delete_document tool. The agent extracts this from your Pydantic model to ensure the delete operation targets the correct partition.

Your Cosmos DB JSON documents are processed entirely in memory within your Python runtime and the secure Vinkius MCP sandbox. No raw data is logged or cached on external servers.

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