Goldbeater

ai.goldbeaterv1.0.0Updated Oct 8, 2026

Goldbeater's daily Google Ads audit, read-only: each finding, its evidence, its value and its fix.

VerifiedStreamable HTTPWeb executableData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Read-only daily Google Ads audit findings, with evidence, estimated value and suggested fixes, exposed to an assistant.

What it does
Goldbeater provides a read-only daily audit of Google Ads accounts. According to its description, it returns each finding together with its supporting evidence, the value attached to it, and a recommended fix. No individual tools are listed in the supplied manifest, so the exact tool set is not documented here.
When to use it
Worth considering when an assistant should review Google Ads performance and surface issues, wasted spend or optimization opportunities without changing anything in the account. Suited to recurring audit and reporting conversations rather than campaign editing.
Requirements
A remote MCP endpoint at over streamable HTTP; no packages, environment variables or headers are declared. The manifest declares no authentication, so how a Google Ads account is linked is not stated. Network access to the provider is required.
Before you install
The audit is described as read-only, so it should not modify campaigns, budgets or bids. The manifest declares no authentication or credentials, which is unusual for a service that reads advertising account data; confirm with the provider how accounts are connected and what data leaves your environment before installing.

Installation

In SourceWeft

  1. Open Goldbeater in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "goldbeater": {
      "type": "http",
      "url": "https://api.goldbeater.ai/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 8, 2026