How to Use the Intercom MCP in Mastra AI

Q: How do I implement human-in-the-loop approvals for Intercom replies in Mastra AI?

Set requireToolApproval to true when registering the replytoconversation tool in your agent config. Mastra will pause the execution loop and wait for an admin confirmation before posting the message.

Q: Can a Mastra AI workflow search Intercom contacts automatically?

Yes, you use searchcontacts within a workflow step to locate a customer by their email. The workflow can then conditionally branch, routing the ticket differently depending on whether the contact exists.

Q: How do I register this MCP Server with my Mastra agent?

Instantiate MCPClient with your Vinkius server URL, then call mcpClient.listTools() and spread the returned array into your agent's tools configuration. The client handles the SSE transport connection automatically.

Build resilient support workflows in Mastra AI that connect directly to our Intercom 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 Intercom MCP to Mastra AI

Create your Vinkius account to connect Intercom 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 Intercom with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient conversation routing in Mastra AI

The `list_conversations` tool retrieves all open tickets to feed your Mastra AI workflow engine. This allows you to build multi-step pipelines that analyze incoming support issues, sort them by urgency, and route them to the correct team. If the Intercom API rate limits your request, Mastra's built-in retry mechanism backs off and tries again automatically. You can chain this with `get_conversation` to extract the full chat history before deciding whether to escalate the ticket.

Human-approved support replies

The `reply_to_conversation` tool posts answers back to customer threads after your agent generates a response. To prevent hallucinations, you configure `requireToolApproval` in Mastra to pause the workflow until an admin reviews the draft. This MCP Server setup ensures no automated message goes live without human eyes on it. Once approved, the workflow resumes and executes the tool, instantly notifying the customer in their inbox.

Automated customer tag synchronization

The `list_tags` tool fetches your existing support labels so your agent can categorize users accurately. Your workflow can branch based on what it finds; for instance, if a contact has a VIP tag, Mastra triggers an immediate Slack alert. You can combine this with `list_companies` to identify high-value accounts automatically. The agent updates the contact record and applies the appropriate tag, keeping your sales and support databases completely aligned.

Setup guide

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

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

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

Set `requireToolApproval` to true when registering the `reply_to_conversation` tool in your agent config. Mastra will pause the execution loop and wait for an admin confirmation before posting the message.

Yes, you use `search_contacts` within a workflow step to locate a customer by their email. The workflow can then conditionally branch, routing the ticket differently depending on whether the contact exists.

Mastra's workflow engine uses automatic exponential backoff for all tool executions. If `list_conversations` hits a rate limit, the framework waits and retries the request without failing the entire run.

Instantiate `MCPClient` with your Vinkius server URL, then call `mcpClient.listTools()` and spread the returned array into your agent's tools configuration. The client handles the SSE transport connection automatically.

Yes, all retrieved contact records and company profiles are processed in a zero-trust, isolated environment. Vinkius secures the credentials using hardware-level encryption keys, ensuring your customer database is never exposed to third-party logs.

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