Can I record a single event using this agent?

Yes, the `record_event` tool allows you to send a JSON object representing your event directly to any named collection.

How do I calculate the average value of a property?

Use the `average_property` tool by specifying the collection name and the numeric target property you want to average.

Is it possible to see my project's collections?

Absolutely. The `list_collections` tool retrieves a list of all event types (collections) currently stored in your Keen project.

Keen MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Keen
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Keen 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 Keen "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Keen?"
    )
    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 Keen MCP Server

Connect your Keen.io project to any AI agent to automate data collection and analysis. This MCP server allows your agent to record events and run complex analytical queries (count, sum, average, etc.) directly from natural language.

Pydantic AI validates every Keen tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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

Event Recording — Send custom event data to any collection in your project instantly
Compute Metrics — Run aggregation queries like count, sum, and average on your event data
Data Discovery — List all event collections, saved queries, and cached datasets
Insight Extraction — Retrieve unique values for specific properties to understand data distribution
Project Oversight — Get comprehensive metadata and configuration details for your Keen project

The Keen MCP Server exposes 10 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 Keen to Pydantic AI via MCP

Follow these steps to integrate the Keen 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 10 tools from Keen with type-safe schemas

Why Use Pydantic AI with the Keen MCP Server

Pydantic AI provides unique advantages when paired with Keen 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 Keen integration code

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

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

Keen + Pydantic AI Use Cases

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

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

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

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

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

Keen MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Keen to Pydantic AI via MCP:

average_property

Calculate average of a property

count_events

Count total events in a collection

count_unique

Count unique values for a property

get_project_details

Get project configuration and details

list_collections

List all event collections

list_datasets

List cached datasets

list_saved_queries

List all saved queries

record_event

Record a single event to a collection

select_unique

List all unique values for a property

sum_property

Sum numeric values of a property

Example Prompts for Keen in Pydantic AI

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

"Record a 'purchase' event with price 99.99 and user 'user_123' in Keen."

"What is the total count of 'page_view' events?"

"Show me all saved queries in my project."

Troubleshooting Keen MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Keen + Pydantic AI FAQ

Common questions about integrating Keen 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 Keen MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.