How to Use the Insightful MCP in Pydantic AI

Q: How do I initialize the Insightful toolset in Pydantic AI?

Use the MCPToolset class with your Vinkius MCP HTTP endpoint. Pass this toolset directly into the toolsets argument when initializing your agent.

Q: Can I use Pydantic AI to monitor Insightful webhook configurations?

Yes, you can query listwebhooks to audit your active notifications. The framework validates the webhook payload structures against your defined Python schemas.

Validate every Insightful productivity metric at runtime with type-safe Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Insightful MCP to Pydantic AI

Create your Vinkius account to connect Insightful 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 Insightful with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate employee directories using Pydantic AI.

The `list_employees` tool retrieves your entire staff roster directly into Pydantic AI's type-checking validation engine. Your agent calls `get_employee` to fetch granular details on a single worker, ensuring every returned field matches your Python models. If the API returns a missing field or an unexpected data type, your agent raises a validation error immediately. This prevents corrupted worker records from entering your downstream workflows.

Enforce strict schemas on this MCP Server.

This MCP Server provides `get_attendance` to return structured time-tracking records that map perfectly to your Pydantic schemas. Your agent uses `get_productivity` alongside it to verify that active hours correspond to valid work metrics. Because every response is validated at runtime, you avoid silent data corruption. Your agent will never hallucinate productivity scores or misinterpret clock-in times because the data must pass your strict type constraints first.

Parse active work logs safely.

The `list_activity` tool streams raw work logs directly into your agent's decision loop. Your agent correlates these logs with active assignments fetched via `list_tasks` to verify that your team is focusing on the right priorities. You can monitor these connections safely because the framework validates the structure of every task and activity log. If a team structure from `list_teams` changes, your code catches the schema shift before it breaks your pipeline.

Setup guide

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

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

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

Use the `MCPToolset` class with your Vinkius MCP HTTP endpoint. Pass this toolset directly into the `toolsets` argument when initializing your agent.

The agent throws a validation error immediately. This stops the run before your agent can act on malformed data, ensuring complete operational safety.

Yes, the framework supports both streamable HTTP and SSE connections. You just need to configure your Vinkius endpoint to use your preferred transport method.

Yes, you can query `list_webhooks` to audit your active notifications. The framework validates the webhook payload structures against your defined Python schemas.

Your attendance records and productivity metrics are validated locally in your runtime environment. Vinkius secures the API credentials using an isolated sandbox, ensuring your private employee data never leaves your verified network.

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