How to Use the Goodcall MCP in Mastra AI

Q: How do I handle failed booking retries with Goodcall and Mastra AI?

You wrap the listbookings tool inside a Mastra workflow that includes automatic retry logic. If the initial lookup fails or times out, the framework backs off and tries again before alerting your team.

Q: Can I build automated phone follow-ups using Goodcall and Mastra AI?

Yes, you can set up a workflow that periodically queries listmissedcalls to find abandoned phone calls. The workflow then uses getcallsummary to understand the caller's intent and trigger an automated SMS or email response.

Q: How do I register the phone tools inside a Mastra agent?

Initialize the MCP client with your endpoint URL, call listTools(), and spread those tools directly into your agent's configuration. The agent can then use tools like getanalytics to report on phone performance autonomously.

Q: Where are my phone call analytics stored during execution?

Voice call metadata and analytics gathered via getanalytics are transmitted over TLS 1.3 and processed in transient, single-tenant memory. No call data is cached or written to persistent storage on the Vinkius MCP hosting layer.

Automate failed booking retries and phone escalation workflows using Mastra AI and the Goodcall 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 Goodcall MCP to Mastra AI

Create your Vinkius account to connect Goodcall 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 Goodcall with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fail-safe booking workflows with Mastra AI

The `list_bookings` tool allows your workflow to detect scheduling conflicts and offer alternative slots to callers. When a caller tries to book an appointment but the slot is taken, you need a smart backup plan. Mastra AI uses its conditional branching engine to check active slots, spot the conflict, and immediately direct the phone agent to offer alternative times. If the database write fails, the framework automatically triggers retries with exponential backoff. This ensures your phone receptionist never drops a scheduling request because of a temporary network hiccup.

Automated missed call triage and routing

The `list_missed_calls` tool lets your workflow scan for unanswered phone calls and pull caller details automatically. Don't let unanswered phone calls slip through the cracks. Mastra AI can run a scheduled workflow that calls this tool every ten minutes, identifies who got disconnected, and pulls their details using `get_call`. From there, the agent can automatically draft follow-up messages or alert your human team if a high-value customer was left hanging. You build this entire MCP-driven pipeline in TypeScript without writing cron jobs.

Dynamic FAQ syncing for phone agents

The `list_faqs` tool lets you sync your website's knowledge base directly with the phone receptionist's brain. Keep your AI receptionist's answers accurate by syncing your knowledge base automatically. You can build a workflow that fetches your latest business documents and updates the phone agent's knowledge base. If the agent needs deeper context during a call, the workflow pulls the active configuration with `get_agent` to verify what the bot currently knows. It keeps your phone responses aligned with your website copy.

Setup guide

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

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

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

You wrap the `list_bookings` tool inside a Mastra workflow that includes automatic retry logic. If the initial lookup fails or times out, the framework backs off and tries again before alerting your team.

Yes, you can set up a workflow that periodically queries `list_missed_calls` to find abandoned phone calls. The workflow then uses `get_call_summary` to understand the caller's intent and trigger an automated SMS or email response.

You can enable the human-in-the-loop feature on your workflow before calling `update_agent`. This pauses the execution and waits for an admin's OK before changing how the active phone receptionist handles calls.

Initialize the MCP client with your endpoint URL, call `listTools()`, and spread those tools directly into your agent's configuration. The agent can then use tools like `get_analytics` to report on phone performance autonomously.

Voice call metadata and analytics gathered via `get_analytics` are transmitted over TLS 1.3 and processed in transient, single-tenant memory. No call data is cached or written to persistent storage on the Vinkius MCP hosting 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