How to Use the GatherUp MCP in Mastra AI

Q: Can I require human approval before Mastra AI replies to a GatherUp review?

Yes, you can set requireToolApproval on the agent when exposing replytoonlinereview. This prevents the agent from posting replies to Google or Facebook without a manager's green light.

Q: How do I sync multi-location metrics using GatherUp and Mastra AI?

Build a workflow that calls listbusinesslocations and then maps over them with getreviewmetrics. This aggregates branch performance data into a single payload for your reporting tools.

Q: How does the Mastra client connect to this MCP Server?

It uses the MCPClient class to connect via SSE or Streamable HTTP. The framework handles the transport layer automatically once you pass the Vinkius endpoint URL.

Build resilient, auto-retrying review workflows using Mastra AI and the GatherUp 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 GatherUp MCP to Mastra AI

Create your Vinkius account to connect GatherUp 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 GatherUp with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build fault-tolerant review loops with Mastra AI

Initiating `send_review_invite` through Mastra's workflow engine ensures your review invites get delivered even if the API hits a temporary rate limit. The built-in exponential backoff automatically retries failed requests without crashing your background processes. You can chain this with `add_new_customer` to ensure new buyers are registered before the system triggers the invite. If the registration step fails, the workflow pauses, alerts your team, and resumes once the connection is verified.

Automate multi-step feedback routing based on sentiment

Running `list_internal_feedback` lets your agent pull direct customer complaints and analyze their sentiment. From there, Mastra's conditional branching routes positive reviews to public channels while sending negative ones to a human manager. For bad feedback, the agent uses `reply_to_feedback` to draft a recovery message. Because Mastra supports human-in-the-loop approvals, the agent holds the draft until a team member clicks approve in your dashboard.

Keep multi-location business data in sync

Querying `list_business_locations` gives your workflow a complete map of all your physical branches. The agent can loop through this list, calling `get_review_metrics` for each location to identify branches that are falling behind on their ratings. If a branch's score drops below a specific threshold, the workflow triggers `search_all_reviews` to find the exact complaints. This automated auditing runs on a cron job, keeping your regional managers informed without manual reporting.

Setup guide

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

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

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

Mastra AI features a native workflow engine with automatic retries. When `send_review_invite` triggers a rate limit, the framework backs off and retries the call automatically.

Yes, you can set `requireToolApproval` on the agent when exposing `reply_to_online_review`. This prevents the agent from posting replies to Google or Facebook without a manager's green light.

Build a workflow that calls `list_business_locations` and then maps over them with `get_review_metrics`. This aggregates branch performance data into a single payload for your reporting tools.

It uses the `MCPClient` class to connect via SSE or Streamable HTTP. The framework handles the transport layer automatically once you pass the Vinkius endpoint URL.

Yes, because Vinkius manages the authentication layer. Your API token is injected securely at the edge, meaning your Mastra workflows only need a single Vinkius token to access `list_customer_contacts` without exposing raw credentials.

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