How to Use the Chattermill MCP in Mastra AI

Q: How do I add the Chattermill MCP Server to a Mastra AI agent?

Install @mastra/mcp@latest and instantiate new MCPClient with your Vinkius server URL. Call mcpClient.listTools() and spread them directly into your agent's tool array.

Q: Can I require human approval before Mastra AI writes to Chattermill?

Yes, Mastra supports a requireToolApproval flag. You can intercept calls to submitfeedbackresponse so a human teammate must click approve before feedback is logged.

Build automated customer feedback workflows with Mastra AI and the Chattermill 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 Chattermill MCP to Mastra AI

Create your Vinkius account to connect Chattermill 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 Chattermill with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-submit feedback from any Mastra AI agent

The `submit_feedback_response` tool writes new customer comments, scores, and source metadata directly to your Chattermill projects. Mastra workflows can catch incoming support tickets or app store reviews and instantly route them to this tool for centralized tracking. You supply the project key and the raw comment text to initiate the write. If your workflow needs to categorize the source, query `list_feedback_sources` first to tag the feedback correctly before submission.

Trigger conditional workflows on sentiment drops

The `get_chattermill_metric` tool retrieves aggregate NPS and sentiment scores to drive your agent's decision-making loops. If a project's average score drops below your threshold, Mastra's workflow engine can branch automatically to alert your team. You set up a step to check the volume and score metrics daily. When the numbers look bad, the agent triggers an escalation branch, using `list_custom_segments` to isolate which user cohorts are driving the negative sentiment.

Parse themes automatically in Mastra pipelines

The `list_feedback_themes` tool gives your Mastra agents direct access to the machine-learning themes identified in your feedback data using this MCP integration. This allows your background workflows to analyze customer complaints and automatically assign them to specific product teams. By combining this with `list_data_types`, your pipeline knows exactly whether it is dealing with a survey response or an app store review. The agent uses this context to route the issue to the correct department without human intervention.

Setup guide

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

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

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

Install `@mastra/mcp@latest` and instantiate `new MCPClient` with your Vinkius server URL. Call `mcpClient.listTools()` and spread them directly into your agent's tool array.

Yes, Mastra supports a `requireToolApproval` flag. You can intercept calls to `submit_feedback_response` so a human teammate must click approve before feedback is logged.

Mastra's built-in workflow engine automatically handles retries with exponential backoff. If the API rate limits your request, the runner pauses and retries the tool call behind the scenes.

Yes, the Mastra client auto-detects the transport layer. It works out of the box with both Streamable HTTP and SSE endpoints provided by Vinkius.

Your customer feedback comments, NPS scores, and custom segments are transmitted over encrypted TLS directly to your Chattermill account. The Vinkius sandbox acts as a zero-trust pass-through, meaning no feedback text is ever persisted or logged within the execution layer.

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