How to Use the Keen MCP in Mastra AI

Q: How do I connect Keen to my Mastra AI agent?

Initialize the MCPClient from @mastra/mcp with your Vinkius URL. Then, spread the output of mcpClient.listTools() into your agent's tool block so it can call recordevent or averageproperty. Mastra automatically manages the transport connection.

Q: Can I require human approval for Keen database writes in Mastra AI?

Yes, Mastra AI supports requireToolApproval for sensitive actions. You can configure it to pause the workflow whenever the agent tries to call recordevent to write new data. This keeps your telemetry clean and prevents spam.

Q: Does Mastra AI support Keen cached datasets?

Yes, your Mastra agent can run listdatasets to retrieve pre-computed data. This is highly recommended for high-volume workflows. It prevents your agent from hitting rate limits with expensive countunique calls.

Build reliable background workers that query Keen metrics and trigger workflows using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keen MCP to Mastra AI

Create your Vinkius account to connect Keen to Mastra 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 Keen with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Mastra AI workflows when events drop

The `count_events` tool checks volume levels, allowing Mastra AI to trigger secondary workflows if traffic dips. You can build automated alerts that run on a cron job. If the event count is too low, the agent can look at `list_collections` to see if a specific tracker stopped sending data. This keeps your monitoring stack entirely autonomous.

Run conditional logic on Keen data using Mastra AI

This MCP server lets your Mastra agent use `sum_property` to calculate total checkout values before deciding to escalate an issue. The agent branches its execution based on the numeric result. You can set up retries with exponential backoff for failed database writes. Mastra handles the network hiccups while Keen records the event.

Auto-generate reports from saved queries

The `list_saved_queries` and `list_datasets` tools let Mastra agents fetch cached reports without manual intervention. This MCP integration allows your agent to run these queries daily and compile markdown summaries. Instead of writing custom cron scripts, you let the agent manage the schedule. It pulls the exact dataset it needs and formats it for your team.

Setup guide

Set up Keen MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Keen tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "keen-mcp-client",
  servers: {
    "keen-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Keen Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Keen tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Keen transactions"
);
console.log(result.text);

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 Keen. 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 Keen 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 Keen MCP in Mastra AI

Initialize the `MCPClient` from `@mastra/mcp` with your Vinkius URL. Then, spread the output of `mcpClient.listTools()` into your agent's tool block so it can call `record_event` or `average_property`. Mastra automatically manages the transport connection.

Yes, Mastra AI supports `requireToolApproval` for sensitive actions. You can configure it to pause the workflow whenever the agent tries to call `record_event` to write new data. This keeps your telemetry clean and prevents spam.

Yes, your Mastra agent can run `list_datasets` to retrieve pre-computed data. This is highly recommended for high-volume workflows. It prevents your agent from hitting rate limits with expensive `count_unique` calls.

Mastra AI has a built-in workflow engine that handles retries with exponential backoff. If `record_event` fails due to network issues, Mastra pauses and tries again. Your analytics data remains accurate even during transient outages.

Your Keen project ID and API keys are stored as encrypted environment variables on Vinkius. The MCP server uses these keys locally within a zero-trust sandbox to authenticate calls like `get_project_details`. No telemetry payloads are logged 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