How to Use the Basin MCP in Pydantic AI

Q: How do I initialize Basin with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset with your Basin endpoint URL and pass it into your Agent's toolsets array.

Q: Can Pydantic AI fetch the newest Basin submission?

The agent uses the getlatestsubmission tool to grab the most recent entry. It then validates the payload against your Pydantic schema.

Q: Does Pydantic AI support restoring spam submissions in Basin?

Yes. The agent calls the markasnotspam tool to move a falsely flagged record back into your active inbox.

Connect Basin to Pydantic AI for type-safe form management, strict validation, and automated lead processing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Basin MCP to Pydantic AI

Create your Vinkius account to connect Basin 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 Basin with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch Type-Safe Leads

Your Python application pulls records using the `get_submission` and `list_submissions` tools. Pydantic AI validates every single field Basin returns against your custom models before the agent can even look at it. If the API sends a malformed email address or a missing name, the framework fails loudly. You never have to worry about silent data corruption or hallucinated form fields breaking your downstream logic.

Control Inbox Spam

Agents clean up your inbox using the `mark_as_spam` and `mark_as_not_spam` tools. Your agent evaluates the text of a submission, scores it, and updates the status in Basin instantly. When the agent decides a record is complete garbage, it can fire the `delete_submission` tool. Because Pydantic AI enforces strict typing, the agent will never try to delete a submission ID that doesn't exist.

Manage Webhooks via MCP Server

Managing external syncs via this Basin MCP Server depends on the `refire_webhooks` tool. Your agent verifies a lead passes all validation checks, then manually triggers the webhook to push that data to your CRM. Checking connection health is built into the workflow. The agent runs `get_account_check` on startup to guarantee the Basin endpoint is live before attempting to process any new form entries.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp]. Create an MCPToolset with your Basin endpoint URL and pass it into your Agent's toolsets array.

The agent uses the get_latest_submission tool to grab the most recent entry. It then validates the payload against your Pydantic schema.

Pydantic AI throws a runtime validation error immediately. The agent halts execution instead of passing bad data to your application.

Yes. The agent calls the mark_as_not_spam tool to move a falsely flagged record back into your active inbox.

Vinkius routes the form submissions through an isolated, ephemeral sandbox. Customer emails and phone numbers are never logged or stored on our 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