Skip to main content
Glama
Rana-X

SF Cleaning Service

by Rana-X
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

IRL - SF Cleaning Service

IRL - A Model Context Protocol (MCP) server for booking cleaning services in San Francisco. Can be deployed locally or to Vercel for remote access.

Setup

1. Install Dependencies

npm install

2. Set Up Resend API

  1. Create Resend Account: Go to https://resend.com and sign up

  2. Get API Key:

    • Navigate to your Resend Dashboard

    • Go to "API Keys" section

    • Create a new API key or copy your existing one

    • It will look like: re_BcASVtoX_Bj4QhZei4xSjyyLr21vhMbVd

  3. Verify Domain (Required for custom email):

3. Configure Email Credentials

Edit .env file with your Resend credentials:

RESEND_API_KEY=re_xxxxxxxxxxxxxxxxxx
FROM_EMAIL=gwen@irl-concierge.com
PARTNER_EMAILS=partner1@example.com,partner2@example.com

Note: You must verify the domain irl-concierge.com in Resend before you can send from gwen@irl-concierge.com. Until verified, use onboarding@resend.dev for testing.

4. Configure Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "sf-cleaning": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-sf-cleaning/index.js"]
    }
  }
}

Replace /absolute/path/to/mcp-sf-cleaning/index.js with the actual path to your index.js file.

5. Restart Claude Desktop

After configuration, restart Claude Desktop to load the MCP server.

Related MCP server: Airbnb MCP Server

Vercel Deployment (For Remote Access)

1. Install Vercel CLI

npm install -g vercel

2. Set Environment Variables

cd /Users/rana/Downloads/IRL/mcp-sf-cleaning

# Set up Vercel environment variables
vercel env add RESEND_API_KEY
# Enter: re_BcASVtoX_Bj4QhZei4xSjyyLr21vhMbVd

vercel env add FROM_EMAIL  
# Enter: gwen@irl-concierge.com

vercel env add PARTNER_EMAILS
# Enter: ranadaytoday@outlook.com

3. Deploy to Vercel

vercel --prod

Follow the prompts:

  • Set up and deploy? Y

  • Which scope? (select your account)

  • Link to existing project? N

  • Project name? irl

  • Directory? ./

  • Want to modify settings? N

4. Get Your MCP Server URL

After deployment, you'll get a URL like:

https://mcp-sf-cleaning.vercel.app

5. Add to Claude Desktop as Custom Connector

  1. Open Claude Desktop

  2. Go to Settings → Connectors

  3. Click "Add custom connector"

  4. Enter:

    • Name: SF Cleaning Service

    • Remote MCP server URL: https://mcp-sf-cleaning.vercel.app/api/mcp

  5. Save and restart Claude

Testing the Remote Server

You can test the API directly:

# List tools
curl -X POST https://mcp-sf-cleaning.vercel.app/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"method":"tools/list"}'

# Request cleaning (SF address)
curl -X POST https://mcp-sf-cleaning.vercel.app/api/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "method": "tools/call",
    "params": {
      "name": "request_cleaning",
      "arguments": {
        "name": "John Doe",
        "phone": "415-555-1234",
        "address": "123 Market St, SF 94105"
      }
    }
  }'

Test Conversation Examples

Example 1: San Francisco Address (Accepted)

You: Can you book a cleaning service for me?
Claude: I'll help you book a cleaning service. I'll need your name, phone number, and address.

You: Name is John Doe, phone is 415-555-0123, address is 123 Market St, San Francisco, CA 94105
Claude: [Uses request_cleaning tool]
Result: ✅ Sent! John Doe, they'll call 415-555-0123 within 1 hour.

Example 2: Non-SF Address (Rejected)

You: Book cleaning for Sarah Smith, 510-555-9876, 456 Broadway, Oakland, CA 94607
Claude: [Uses request_cleaning tool]
Result: Sorry, we only serve San Francisco currently. We're expanding - stay tuned!

Example 3: SF Zip Code Detection

You: I need cleaning at 789 Pine Street, 94108. Name: Alice Wong, Phone: 415-555-3456
Claude: [Uses request_cleaning tool]
Result: ✅ Sent! Alice Wong, they'll call 415-555-3456 within 1 hour.

Usage

The server provides one tool:

  • request_cleaning: Books cleaning service for SF addresses only

Parameters:

  • name: Customer name

  • phone: Contact phone number

  • address: Service address (must be in San Francisco)

Responses:

  • SF Address: "✅ Sent! [name], they'll call [phone] within 1 hour."

  • Non-SF Address: "Sorry, we only serve San Francisco currently. We're expanding - stay tuned!"

How It Works

  1. Checks if address contains "sf", "san francisco", or SF zip codes (940xx, 941xx)

  2. If in SF: Sends email via Resend API to partners and confirms booking

  3. If not in SF: Returns polite rejection message

Why Resend?

  • Simple API: Clean, modern email API designed for developers

  • No SMTP hassles: No need for app passwords or complex SMTP settings

  • Better deliverability: Built-in SPF, DKIM, and DMARC support

  • Free tier: 3,000 emails/month free, perfect for small projectsTest auto-deployment

Available Tools

1 tool
request_cleaningC

Request cleaning service in San Francisco

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesCustomer name
phoneYesPhone number (10-digit US format)
addressYesService address in San Francisco

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the geographic constraint ('in San Francisco') but doesn't describe what happens after the request is made (e.g., confirmation, scheduling, costs), whether authentication is required, or any rate limits. This leaves significant gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without any unnecessary words. It's appropriately sized and front-loaded with the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what the tool returns, potential side effects, error conditions, or any behavioral context beyond the basic action, leaving the agent with incomplete information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter information beyond what's in the schema, maintaining the baseline score for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Request cleaning service') and geographic scope ('in San Francisco'), providing a specific verb+resource combination. However, with no sibling tools mentioned, there's no opportunity to demonstrate differentiation from alternatives, which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or any contextual limitations beyond the geographic scope mentioned. It simply states what the tool does without offering usage instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • First observedrequest_cleaning
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'request_cleaning' has a clear, distinct purpose that cannot be confused with any other tool in this set.

Naming Consistency5/5

The naming pattern is trivially consistent since there is only one tool. The tool name 'request_cleaning' follows a clear verb_noun convention, and with no other tools to compare, there is no inconsistency.

Tool Count2/5

A single tool is generally too few for a server's purpose, as it limits functionality and suggests an incomplete or thin surface. For a 'SF Cleaning Service' domain, one might expect additional tools for operations like scheduling, pricing, or status checks, making this count inappropriate for the apparent scope.

Completeness2/5

The tool set is severely incomplete for a cleaning service domain. While 'request_cleaning' covers initiation, there are obvious gaps such as checking service status, modifying or canceling requests, viewing pricing, or managing schedules. This will likely cause agent failures in handling full workflows.

Resources

Related MCP Connectors

Related MCP Servers