How to Use the 100ms MCP in Mastra AI

Q: How do I find a room ID using Mastra?

Your agent uses listrooms to search for the correct identifier based on your input. It then uses that ID to perform further actions like checking session details.

Q: Can I use 100ms recordings in my Mastra workflow?

Use listrecordings to pull metadata about your cloud-stored videos. Your agent can then trigger follow-up actions like notifying your team or updating a dashboard.

Mastra AI agents manage your 100ms video rooms with automated workflows, retries, and conditional logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 100ms MCP to Mastra AI

Create your Vinkius account to connect 100ms 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 100ms with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute complex meeting workflows

Your Mastra agents chain `create_room` and `update_room` calls to handle multi-step scheduling. You set up conditions where the agent retries the request if the infrastructure is temporarily busy. You avoid manual intervention during room setup. The workflow engine keeps your video infrastructure consistent even if network conditions fluctuate.

Automate participant management

Your agents monitor active sessions by calling `list_peers` and trigger `remove_peer` if a user exceeds session limits. You define the rules in your Mastra workflow, and the agent enforces them. You stop manually checking who is in a call. The agent handles the cleanup, keeping your sessions focused and secure.

Audit session history automatically

Your agent runs a daily workflow to pull `list_sessions` and `list_recordings` for your records. It processes the data and stores the metadata in your internal database. You eliminate the tedious task of manual log gathering. The agent does the heavy lifting while you focus on building features.

Setup guide

Set up 100ms 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 100ms 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: "100ms-mcp-client",
  servers: {
    "100ms-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "100ms Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to 100ms tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent 100ms 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 100ms. 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 100ms 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 100ms MCP in Mastra AI

Import the MCP client into your Mastra project and add the 100ms server URL to your agent configuration. Your agent will auto-detect the tools and make them available for your workflow definitions.

Yes, you can enable human-in-the-loop approvals for any sensitive 100ms operation. This ensures you confirm room updates or participant kicks before the agent executes them.

Your agent uses `list_rooms` to search for the correct identifier based on your input. It then uses that ID to perform further actions like checking session details.

Use `list_recordings` to pull metadata about your cloud-stored videos. Your agent can then trigger follow-up actions like notifying your team or updating a dashboard.

Your room settings are protected by sandboxed execution, meaning no trace of your configuration remains after the agent finishes its task. This ephemeral approach keeps your infrastructure management private and secure.

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