mcpField
🤖
🤖 AsyncPraiseRebuke MCP Server

🤖 AsyncPraiseRebuke MCP Server

Local
github.com/fabianwilliamsBusiness & Marketing0Updated 80w ago
Repository

About 🤖 AsyncPraiseRebuke MCP Server

AsyncPraiseRebuke MCP Server exposes business reviews and contact-discovery workflows for MCP clients. Its tools search feedback, inspect business ratings, and find and log contact emails, including through an agent-driven multi-step flow.

Key features

  1. 01List and search public reviews
  2. 02View top- and low-rated businesses
  3. 03Search the business directory
  4. 04Discover business contact emails
  5. 05Log contacts and directory entries
  6. 06Automate discovery and duplicate checks

Use cases

  1. 01Find reviews by business name
  2. 02Compare highly and poorly rated locations
  3. 03Find contact emails from business websites
  4. 04Record newly discovered businesses in the directory

MCP support

Exposes review, directory, and contact-discovery tools to Claude Desktop and other MCP-compatible clients. An agent tool chains website discovery, duplicate checking, and directory logging.

#asyncpraiserebuke#mcp#business-feedback

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "asyncpraiserebuke": {
      "command": "npx",
      "args": [
        "-y",
        "@fabianwilliams/asyncpraiserebuke-mcp"
      ]
    }
  }
}
Run commandnpx -y @fabianwilliams/asyncpraiserebuke-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@fabianwilliams/asyncpraiserebuke-mcp

Tools

6

Saved tool list · updated 3w ago

This tool takes no parameters.

Details

From the project README

🤖 AsyncPraiseRebuke MCP Server

AsyncPraiseRebuke-MCP is a Model Context Protocol (MCP) server that exposes business feedback and contact discovery tools — including AI agent-based flows — for integration with Claude Desktop or any other MCP-compliant client.

🔍 What It Does

This server powers tools that can:

  • ✅ List and search customer feedback reviews
  • ✅ View top-rated and lowest-rated establishments
  • ✅ Discover business contact emails using scraping and heuristics
  • ✅ Log new entries to a Cosmos DB-based directory
  • ✅ Chain tool logic with agents that automate multi-step flows

🧩 Available Tools

Core Tools (Stateless & Reusable)

These can be used individually for focused functionality:

  • `listPublicReviews` – Get all public feedback entries
  • `getTopRatedLocations` – View top and bottom rated businesses
  • `searchReviews` – Search reviews by partial business name
  • `searchBusinessDirectory` – Look up existing business entries in Cosmos DB
  • `logBusinessEmail` – Add a business contact email manually
  • `discoverBusinessEmail` (from ClicknContact) – Discover emails and form fields from business websites
🧠 Agent Tool: `discoverAndLogBusinessEmail`

This agentized tool automates the entire workflow:

  1. Calls ClicknContact to discover contact info
  2. Checks your Cosmos DB directory to prevent duplicates
  3. Logs new businesses with placeholder values if needed

Tool name: `discoverAndLogBusinessEmail`
Source: `ClicknContactScannerAgent`

🚀 Getting Started

npm install -g @fabianwilliams/asyncpraiserebuke-mcp

Then add to your Claude Desktop config:

"ClicknContactScannerAgent": {
  "command": "npx",
  "args": [
    "--yes",
    "@fabianwilliams/asyncpraiserebuke-mcp",
    "scanAndLogNewBusinessEmails"
  ],
  "env": {
    "REVIEW_API_KEY": "your-key-here",
    "REVIEW_API_BASE_URL": "https://your-api.com/api"
  }
}

You can also run this manually:

npx --yes @fabianwilliams/asyncpraiserebuke-mcp scanAndLogNewBusinessEmails

🛠 Dev Structure

/src
  apiClient.ts       // Cosmos-backed endpoint calls
  main.ts            // MCP tool definitions
  types.ts           // Shared types
  scanAndLogNewBusinessEmails.ts // CLI agent wrapper

/test
  businessesToScan.json // Sample test data

🧪 Testing the Agent

Make sure dependencies are installed and build the project:

npm install
npm run build

Then run:

npx @fabianwilliams/asyncpraiserebuke-mcp scanAndLogNewBusinessEmails

Or test via Claude Desktop:

Please scan the following websites for contact emails and log any new ones not already in the directory: https://example1.com, https://example2.com

📦 Publishing

For maintainers:

npm version patch  # or minor / major
npm publish --access public

🪪 License

MIT — use it, fork it, agentify it.

Built with ❤️ by @fabianwilliams

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.