How to Use the Collect MCP in Mastra AI

Q: How do I register the Collect MCP Server tools inside Mastra AI?

Initialize the MCP client, call listTools(), and spread them directly into your Mastra Agent's tool array. The framework automatically registers all ten tools for your workflows.

Q: Can Mastra AI require approval before running Collect tools?

Yes, you can set requireToolApproval on destructive tools like createrequest. This pauses the workflow and alerts a human before any external emails go out.

Q: Where is my team information and document metadata stored?

All team details accessed via getteaminfo are processed in ephemeral memory. The Vinkius sandbox ensures zero persistent storage of your sensitive collection metadata.

Build automated document gathering workflows with Mastra AI and this Collect 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 Collect MCP to Mastra AI

Create your Vinkius account to connect Collect 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 Collect with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate multi-step file requests with Mastra AI

`create_request` acts as the trigger for complex, multi-step document workflows inside your Mastra agents. If a customer fails to upload a required file, Mastra's workflow engine catches the failure and automatically retries the request. You can set up conditional branches that check `get_element_details` to verify if the submitted data matches your schema. If a field is missing, the agent routes the workflow to a human-in-the-loop approval step.

Smart campaign monitoring with backoff retries

`list_campaigns` lets your Mastra agent poll for active data gathering drives on a schedule. The built-in workflow engine handles API rate limits by applying exponential backoff whenever you query large campaigns. If a network hiccup occurs while running `get_campaign`, Mastra automatically retries the execution. Your autonomous pipelines keep running without crash alerts or lost data.

Human-in-the-loop verification for incoming data

`get_request` retrieves the exact state of a user's submission before your workflow moves to the next step. Mastra's human-in-the-loop feature pauses the agent until an admin approves the gathered documents. Once approved, your agent can run `send_message` to notify the client of a successful upload. This keeps your automated processes safe from incorrect or malicious file submissions.

Setup guide

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

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

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

Initialize the MCP client, call `listTools()`, and spread them directly into your Mastra Agent's tool array. The framework automatically registers all ten tools for your workflows.

Yes, you can set `requireToolApproval` on destructive tools like `create_request`. This pauses the workflow and alerts a human before any external emails go out.

The framework uses built-in workflow retries to handle temporary API downtime. If `list_requests` fails, Mastra retries the call using your configured backoff strategy.

No, the client automatically detects whether to use Streamable HTTP or SSE. You only need to supply the Vinkius URL during initialization.

All team details accessed via `get_team_info` are processed in ephemeral memory. The Vinkius sandbox ensures zero persistent storage of your sensitive collection metadata.

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