How to Use the CockroachDB Cloud MCP in Pydantic AI

Q: How do I set up CockroachDB Cloud tools in Pydantic AI?

Install pydantic-ai-slimmcp and define your Vinkius MCP Server toolset pointing to the hosted URL. Pass this toolset into your Agent constructor to give your python code type-safe access to your database clusters.

Q: How are my CockroachDB Cloud cluster profiles protected during validation?

Your profile details retrieved by getmycockroachprofile are processed in memory during the validation step. Vinkius secures this data in a zero-trust, ephemeral sandbox that never writes your credentials to disk.

Run type-safe CockroachDB Cloud operations with Pydantic AI agents that validate every database response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CockroachDB Cloud MCP to Pydantic AI

Create your Vinkius account to connect CockroachDB Cloud 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 CockroachDB Cloud with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate database cluster states with Pydantic AI

Never trust unstructured LLM outputs when managing databases. Your MCP-enabled agent calls `get_cluster_cloud_details` and `get_my_cockroach_profile` to pull cluster metadata, validating the response schema instantly. If the API returns unexpected fields, Pydantic AI raises a validation error immediately. This prevents your agent from acting on corrupted or hallucinated database states.

Safe network perimeter checks using an MCP Server

Secure your database connections without silent failures. Your agent queries `list_network_allowlist` and parses the allowed IP addresses against strict Pydantic IP models. This ensures your network rules strictly match your security policies. The agent rejects any input that fails validation, keeping your cloud firewall rules perfectly predictable.

Track cluster scaling and key management safely

Monitor active upgrades with confidence. The agent runs `list_cluster_operations` and `list_encryption_keys` to track running tasks and customer-managed keys. Every operation payload is parsed into typed Python models. Your agent won't mistake a pending upgrade for a completed one because the status field is strictly validated at runtime.

Setup guide

Set up CockroachDB Cloud 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": {
        "cockroachdb-cloud-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]` and define your Vinkius MCP Server toolset pointing to the hosted URL. Pass this toolset into your `Agent` constructor to give your python code type-safe access to your database clusters.

The framework fails loudly. Instead of letting your agent hallucinate, Pydantic AI throws a validation error, forcing your agent to handle the schema mismatch gracefully.

Yes. The framework fully supports async execution. When your agent calls `list_cockroach_clusters` or `list_cluster_nodes`, it runs concurrently without blocking your main application event loop.

No. The Vinkius MCP Server hosts the API connection for you. Your agent connects over a secure HTTP or SSE transport, removing the need for local database drivers.

Your profile details retrieved by `get_my_cockroach_profile` are processed in memory during the validation step. Vinkius secures this data in a zero-trust, ephemeral sandbox that never writes your credentials to disk.

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