How to Use the Countly MCP in Mastra AI

Q: How do I require human approval before Mastra AI records a Countly event?

Set the requireToolApproval option on the recordevents tool within your MCP agent setup. The agent will pause and wait for a green light before writing any data.

Build resilient, automated analytics workflows with Mastra AI and this Countly MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Countly MCP to Mastra AI

Create your Vinkius account to connect Countly 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 Countly with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branching session workflows in Mastra AI

Mastra's workflow engine excels at handling multi-step logic. You can build an agent that runs `begin_session` and then branches depending on the user's subscription tier. If a network hiccup occurs, the framework automatically retries the action with exponential backoff. Your session tracking stays accurate even when external APIs get flaky.

Guardrails for recording custom events

Sometimes you don't want an autonomous agent writing data to your analytics platform without supervision. You can use this MCP Server to require approval before executing `record_events`. This ensures your clean data stays clean. The agent drafts the event payload, a human verifies it, and only then does the system commit the write.

Query Countly metrics via autonomous Mastra agents

Running deep analytics queries used to mean digging through dashboards. Now, your agent can execute `read_drill` or `read_metrics` to grab specific behavioral cohorts on a schedule. You can feed these metrics directly into another workflow step. For example, if active users drop below a threshold, the agent can instantly trigger a Slack alert.

Setup guide

Set up Countly 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 Countly 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: "countly-mcp-client",
  servers: {
    "countly-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Countly 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 Countly. 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 Countly 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 Countly MCP in Mastra AI

Install @mastra/mcp and instantiate MCPClient with the Vinkius URL. From there, spread the tools directly into your agent configuration so it can access functions like read_events.

Yes, Mastra's built-in engine handles retries out of the box. If update_session fails due to a network glitch, the framework retries the call with exponential backoff.

Set the requireToolApproval option on the record_events tool within your MCP agent setup. The agent will pause and wait for a green light before writing any data.

Mastra automatically detects the transport type, supporting both Server-Sent Events (SSE) and Streamable HTTP. You don't need to write any custom transport adapters.

Your custom events and user details are processed inside a zero-trust MCP sandbox. Vinkius never stores this telemetry, ensuring your raw data moves directly to your analytics endpoint.

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