How to Use the Deskpro MCP in Mastra AI

Q: Can I require human approval before Mastra AI modifies a Deskpro ticket?

Yes. By setting requireToolApproval on the updateticketproperties tool, Mastra AI pauses execution. Your agent waits for a human to confirm the changes before modifying the live support ticket.

Q: Does Mastra AI support Webhook monitoring for Deskpro?

Yes, you can use the listconfiguredwebhooks tool within a workflow to monitor active connections. This helps your agent verify that events are firing correctly before executing automated support routines.

Q: How does this MCP Server secure my Deskpro knowledgebase articles and user data?

Every request to getarticlecontent or listhelpdeskusers runs inside a zero-trust, ephemeral V8 sandbox. No database is attached to the MCP Server, meaning your knowledgebase text and customer emails exist only in transit during the execution window.

Automate complex Deskpro ticket routing and escalation workflows using Mastra AI and this 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 Deskpro MCP to Mastra AI

Create your Vinkius account to connect Deskpro 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 Deskpro with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated ticket triage with Mastra AI

The `list_helpdesk_tickets` tool retrieves unassigned support cases via the MCP Server so your Mastra AI workflows can categorize them automatically. After reading the subject, your agent routes the issue to the correct department based on your pre-defined branching logic. If the initial routing attempt fails, the workflow engine triggers automatic retries with exponential backoff. This ensures your support queue keeps moving even when external network blips occur.

Self-healing ticket updates

The `update_ticket_properties` tool modifies ticket status, department, and priority based on decisions made by your Mastra AI agent. When customer replies come in, the workflow evaluates the text and updates the ticket fields without human intervention. Because Mastra AI handles state transitions natively, you can design workflows that wait for specific conditions before closing a ticket. This prevents agents from abandoning tickets that actually require follow-up.

Human-in-the-loop Deskpro MCP Server workflows

The `create_new_helpdesk_ticket` tool generates support tickets only after receiving manual approval from an administrator in your Mastra AI workflow. You can configure requireToolApproval to pause the agent before it writes new records to your helpdesk. This safeguard lets you audit drafted responses and ticket details before they go live. Once approved, the workflow resumes and writes the data to Deskpro instantly.

Setup guide

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

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

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

You can configure Mastra AI workflow steps to catch errors from tools like update_ticket_properties. If an escalation fails, the workflow uses built-in retry logic to attempt the update again before alerting an admin.

Yes. By setting requireToolApproval on the update_ticket_properties tool, Mastra AI pauses execution. Your agent waits for a human to confirm the changes before modifying the live support ticket.

Instantiate the client using new MCPClient with your Vinkius URL, then spread listTools() into your Mastra AI agent's tool configuration. The agent instantly gains access to tools like get_user_profile and list_helpdesk_tickets.

Yes, you can use the list_configured_webhooks tool within a workflow to monitor active connections. This helps your agent verify that events are firing correctly before executing automated support routines.

Every request to get_article_content or list_helpdesk_users runs inside a zero-trust, ephemeral V8 sandbox. No database is attached to the MCP Server, meaning your knowledgebase text and customer emails exist only in transit during the execution window.

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