How to Use the DoiT MCP in Pydantic AI

Q: How do I register the DoiT MCP server in my Pydantic AI codebase?

Instantiate an MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly into the Agent constructor to expose the cost-tracking tools to your model.

Q: Does Pydantic AI validate the output of DoiT tools?

Yes, every response from tools like getbillingcostsummary is validated against Pydantic models at runtime. If the API schema changes unexpectedly, your agent will fail loudly instead of using corrupt data.

Q: Can my Pydantic AI agent list all connected cloud accounts using DoiT?

Yes, the agent calls listconnectedcloudaccounts to get a structured list of your AWS, GCP, and Azure accounts. The returned data is fully typed, allowing safe downstream processing.

Q: How do I get organization metadata?

Your agent calls getdoitaccountmetadata to pull the active organization details. This helps ensure your agent is running queries against the correct billing scope.

Connect your Pydantic AI agents to the DoiT MCP Server for type-safe multi-cloud cost tracking and anomaly checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DoiT MCP to Pydantic AI

Create your Vinkius account to connect DoiT 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 DoiT with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate cloud budget limits with Pydantic AI

This MCP Server exposes `list_cost_budgets` to let your agent fetch your current budget configurations. Because Pydantic AI enforces type safety, every cost limit and budget name is validated against strict Python models at runtime. If a budget is breached, your agent uses `list_exceeded_cost_budgets` to isolate the problem. You get guaranteed schema correctness, meaning your agent will never crash on malformed billing API payloads.

Detect critical cost spikes in Pydantic AI

The `list_critical_cost_spikes` tool lets your agent identify high-severity cost anomalies that need immediate attention. It gives your type-safe agent a direct feed of urgent infrastructure spending issues. Your agent can run these checks in a cron job, using `list_cost_anomalies` to gather broader historical context. It ensures your team gets notified about cost spikes without false positives from bad data parsing.

Retrieve validated asset details using Pydantic AI

The `get_asset_details` tool fetches configuration and cost data for any specific cloud resource. It returns structured metadata that your agent validates immediately to prevent silent data corruption. Your agent can search for these assets first using `search_cloud_assets` with a name keyword. This two-step process makes it easy to audit specific infrastructure components safely.

Setup guide

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

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

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

Instantiate an `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset directly into the `Agent` constructor to expose the cost-tracking tools to your model.

Yes, every response from tools like `get_billing_cost_summary` is validated against Pydantic models at runtime. If the API schema changes unexpectedly, your agent will fail loudly instead of using corrupt data.

Yes, the agent calls `list_connected_cloud_accounts` to get a structured list of your AWS, GCP, and Azure accounts. The returned data is fully typed, allowing safe downstream processing.

Your agent calls `get_doit_account_metadata` to pull the active organization details. This helps ensure your agent is running queries against the correct billing scope.

Vinkius routes all MCP tool executions through isolated V8 sandboxes with zero-trust networking. Your cloud billing and asset configuration data is processed in-memory and is never stored on 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