@striderlabs/mcp-opentable

Book restaurant reservations via OpenTable using AI agents

Part of Strider Labs — action execution for personal AI agents.

Get Started in 2 Minutes

For Claude Desktop Users

Add this to your Claude Desktop config:

json

{
  "mcpServers": {
    "opentable": {
      "command": "npx",
      "args": ["-y", "@striderlabs/mcp-opentable"]
    }
  }
}

Restart Claude.
Tell Claude: "Book a table for 4 at an Italian restaurant for 7 PM tonight"

Your agent can now book reservations. That's it.

Installation (NPM)

bash

npm install @striderlabs/mcp-opentable

Or with npx directly:

bash

npx @striderlabs/mcp-opentable

Features

🔍 Search restaurants by cuisine, location, and rating
⏰ Check availability for specific times and party sizes
📅 Make reservations with one-click confirmation
📝 View booking history and manage reservations
🏷️ Filter by price, cuisine, and dining style
🔐 Persistent sessions - stay logged in across restarts
🔄 Automatic MFA - handles multi-factor authentication
📱 Per-user credentials - encrypted session storage

Tested & Compatible

Component	Version	Status
MCP SDK	^1.0.0	✅
Node.js	18+	✅
Claude Desktop	Latest	✅
Claude (API)	claude-3.5-sonnet+	✅
Anthropic SDK	^0.20+	✅

Metrics

Weekly downloads: 187 (Apr 10-17, 2026) — Top restaurant connector (+467% growth)
Status: ✅ Live in production
Reliability: 85%+ task completion rate
Discovery: npm, Claude Plugins, mcpservers.org, ClawHub, PulseMCP

Available Elsewhere

npm: npmjs.com/@striderlabs/mcp-opentable
Claude Plugins: Search "Strider Labs" in Claude
mcpservers.org: Strider Labs OpenTable
Full Strider Labs: github.com/striderlabsdev/striderlabs

How It Works

For Agents

Your agent can use these capabilities:

javascript

// Search for restaurants
restaurants = search_restaurants({
  location: "San Francisco, CA",
  cuisine: "Italian",
  price_range: "$$",
  date: "2026-04-15",
  party_size: 4,
  time: "19:00"
})

// Get detailed restaurant info
details = get_restaurant_details({
  restaurant_id: "ristorante-milano-sf"
})

// Check availability
availability = check_availability({
  restaurant_id: "ristorante-milano-sf",
  party_size: 4,
  date: "2026-04-15",
  time: "19:00"
})

// Make a reservation
booking = make_reservation({
  restaurant_id: "ristorante-milano-sf",
  party_size: 4,
  date: "2026-04-15",
  time: "19:00",
  special_requests: "Window seat if possible"
})

// View your reservations
reservations = get_my_reservations()

Session Management

Each user has encrypted, persistent credentials
Automatic OAuth token refresh
MFA handling (SMS/email)
Sessions survive agent restarts

Reliability

85%+ task completion rate
Automated UI change detection (connectors update when OpenTable changes)
Fallback paths for failures
24/7 monitoring + alerting

Configuration

Environment Variables

bash

# Optional: Use a specific OpenTable account
OPENTABLE_EMAIL=your-email@example.com
OPENTABLE_PASSWORD=your-password  # Highly recommend using .env file

Self-Hosted

bash

# Clone the repo
git clone https://github.com/striderlabsdev/mcp-opentable
cd mcp-opentable

# Install dependencies
npm install

# Start the server
npm start

# Your agent can now connect to localhost:3000

Architecture

How We Connect

This connector uses browser automation (Playwright) to interact with OpenTable, because OpenTable doesn't have a comprehensive public API for reservations. Here's why that's safe and reliable: