How to Use the Grain MCP in Mastra AI

Q: How do I register Grain tools inside a Mastra AI agent?

Initialize the MCP Client with your server URL, call mcpClient.listTools(), and spread the returned tools directly into your Mastra AI agent's tool array. This instantly exposes operations like getinsights to the agent's decision-making loop.

Build resilient, self-healing meeting workflows by connecting Grain to Mastra AI agents using 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 Grain MCP to Mastra AI

Create your Vinkius account to connect Grain 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 Grain with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate post-meeting tasks with Mastra AI workflows

The `get_action_items` tool feeds meeting decisions straight into Mastra AI's conditional branching engine. This allows you to build workflows that parse action items and automatically route them to different external task managers based on who is assigned. If the initial sync fails, Mastra's built-in retry mechanism with exponential backoff ensures the action items are not lost. The agent retries the call to the MCP Server without requiring manual intervention from your team.

Search and filter recordings inside Mastra agents

The `search_recordings` tool gives your Mastra AI agent the ability to scan your entire meeting history using natural language queries. The agent can search for specific keywords, locate the exact conversation, and retrieve the context it needs to execute subsequent workflow steps. By registering this tool inside your Mastra agent definition, the model autonomously decides when to search Grain. It can then chain this search with other tools to assemble complete historical reports for your team.

Manage workspace access within Mastra pipelines

The `list_workspace_members` tool lets your Mastra AI workflows verify who belongs to your organization before sharing sensitive meeting insights. This prevents your autonomous agents from accidentally sending transcripts to external Slack channels or email addresses. You can configure a human-in-the-loop gate using Mastra's `requireToolApproval` setting. This pauses the workflow and alerts an admin before the agent shares any meeting data retrieved from the MCP Server.

Setup guide

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

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

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

Initialize the MCP Client with your server URL, call `mcpClient.listTools()`, and spread the returned tools directly into your Mastra AI agent's tool array. This instantly exposes operations like `get_insights` to the agent's decision-making loop.

Yes, Mastra AI features a native workflow engine that manages API rate limits. If a tool like `list_recordings` triggers a rate limit, the workflow automatically pauses and retries the request using backoff logic.

Use Mastra's tool approval middleware to intercept sensitive operations. For instance, you can require an admin to click approve before the agent executes `upload_video` to process external meeting files.

Yes, you can run the MCP Server locally via stdio or host it securely on Vinkius. Mastra AI auto-detects the transport type, allowing your agents to query Grain recordings whether running in development or production.

Your meeting transcripts are processed in memory during the agent's execution cycle and are never persisted by Mastra AI. Communication between Mastra and the MCP Server occurs over TLS-encrypted endpoints, keeping your corporate conversations 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