How can I check the latest lead that submitted a form?

Use the `get_latest_submission` tool. It automatically retrieves the single most recent entry across all your forms, allowing you to respond instantly.

Can the agent filter out spam submissions?

Yes. Use the `mark_as_spam` tool with a Submission ID to flag suspicious entries. You can also use `mark_as_not_spam` to restore entries that were incorrectly flagged.

Is it possible to re-send data to my CRM if it failed?

Yes. Use the `refire_webhooks` tool by providing the Submission ID. This manually triggers any webhooks associated with that form, ensuring your external integrations receive the data.

Basin MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Basin
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Basin through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Basin "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Basin?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Basin MCP Server

Empower your AI agent to orchestrate your entire lead capture workflow with Basin, the powerful form backend for modern websites. By connecting Basin to your agent, you transform static submission data into a natural conversation. Your agent can instantly audit new form entries, identify and flag spam, retrieve specific lead details, and even manually refire webhooks without you ever touching a dashboard. Whether you're managing a single contact page or a complex lead generation network, your agent acts as a real-time submission manager, ensuring your inbound data is always clean and actionable.

Pydantic AI validates every Basin tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Submission Management — List all form submissions across your account or dive deep into specific entry details via natural language.
Spam Control — Instantly mark suspicious entries as spam or unmark false positives to maintain a high-quality lead database.
Form Oversight — List all forms in your Basin account and retrieve detailed metadata for each to map your data collection points.
Webhook Triggers — Manually refire webhooks for specific submissions to ensure your downstream integrations are correctly updated.
Real-time Auditing — Retrieve the single latest submission instantly to respond to new leads with zero delay.

The Basin MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Basin to Pydantic AI via MCP

Follow these steps to integrate the Basin MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Basin with type-safe schemas

Why Use Pydantic AI with the Basin MCP Server

Pydantic AI provides unique advantages when paired with Basin through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Basin integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Basin connection logic from agent behavior for testable, maintainable code

Basin + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Basin MCP Server delivers measurable value.

Type-safe data pipelines: query Basin with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Basin tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Basin and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Basin responses and write comprehensive agent tests

Basin MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Basin to Pydantic AI via MCP:

delete_submission

Permanently delete a submission

get_account_check

Verify Basin connection

get_form

Get details for a specific form

get_latest_submission

Retrieve the single most recent submission

get_submission

Get full details for a specific submission

list_form_submissions

Helper to list submissions for a specific form

list_forms

List all forms in your Basin account

list_submissions

List all submissions across all forms

mark_as_not_spam

Convenience tool to unmark a submission as spam

mark_as_spam

Convenience tool to mark a submission as spam

refire_webhooks

Manually trigger webhooks for a specific submission

update_submission

Update submission metadata (e.g. mark as spam)

Example Prompts for Basin in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Basin immediately.

"Show me the latest submission from my contact forms."

"Mark submission ID 'sub_abc123' as spam."

"List all forms in my Basin account."

Troubleshooting Basin MCP Server with Pydantic AI

Common issues when connecting Basin to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Basin + Pydantic AI FAQ

Common questions about integrating Basin MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Basin MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.