How to Use the Castmagic MCP in Mastra AI

Q: How do I load Castmagic tools into my Mastra AI agent?

Initialize the MCPClient with your Vinkius endpoint URL. Call listTools() on the client and spread the results into your agent's tool array. Mastra auto-detects the Streamable HTTP transport.

Q: How do I pause a Castmagic workflow for human review in Mastra AI?

Set requireToolApproval on the specific tool, like getmagiccontent. The agent will stop execution, ping you for permission, and wait for your go-ahead before generating the final output.

Q: What is the best way to monitor account limits in an MCP Server pipeline?

Add a step in your pipeline that calls getcastmagicaccount before processing new files. If your quota is too low, Mastra can branch the workflow to skip the upload and trigger a Slack notification instead.

Build resilient content workflows in Mastra AI that automatically retry failed Castmagic transcriptions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Castmagic MCP to Mastra AI

Create your Vinkius account to connect Castmagic 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 Castmagic with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient MCP Server Audio Pipelines

Processing massive video files often hits timeouts or rate limits. Hooking this MCP Server into Mastra AI lets you wrap `create_new_transcript` in a workflow with exponential backoff. If the initial submission drops, your agent waits and tries again automatically without crashing the entire script. You build conditional branches based on the response. If the audio is too long, the workflow catches the error and alerts an admin instead of failing silently. Your agent keeps running, handles the exception, and moves on to the next file in the queue.

Chain Content Generation Steps

Raw transcripts rarely represent the final product. Mastra can sequence `get_transcript_details` immediately followed by `get_magic_content` to pull the text and generate the social posts in one fluid motion. The workflow engine ensures step two never fires until step one confirms success. You can even add human-in-the-loop approvals before publishing. Using `requireToolApproval`, the workflow pauses after grabbing the show notes, waits for you to review the draft, and only continues if you hit yes. The automation does the heavy lifting while you keep editorial control.

Audit and Clean Up Storage

Leaving unused audio files on the server wastes money and space. You can schedule a Mastra workflow to run `list_transcripts` every week and identify content older than thirty days. The agent builds a list of stale files and prepares them for deletion. Wiping the data is just another automated step. The workflow iterates through the list and fires `delete_transcript` for each outdated ID. You get a clean workspace without ever manually logging into a dashboard to scrub old recordings.

Setup guide

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

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

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

Initialize the `MCPClient` with your Vinkius endpoint URL. Call `listTools()` on the client and spread the results into your agent's tool array. Mastra auto-detects the Streamable HTTP transport.

The built-in workflow engine handles this natively. You configure the step calling `create_new_transcript` with automatic retries and exponential backoff to survive temporary API hiccups.

Set `requireToolApproval` on the specific tool, like `get_magic_content`. The agent will stop execution, ping you for permission, and wait for your go-ahead before generating the final output.

Add a step in your pipeline that calls `get_castmagic_account` before processing new files. If your quota is too low, Mastra can branch the workflow to skip the upload and trigger a Slack notification instead.

The V8 Isolate Sandbox running on Vinkius processes your audio URLs, speaker lists, and generated social posts in strict isolation. No data persists after the workflow completes, ensuring your raw recordings and notes remain private.

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