Hospitable MCP Server
Connects Claude to the Hospitable API v2 for managing vacation rental properties, reservations, guest messages, and reviews.
README
Hospitable MCP Server - Breezy Beach Stays
MCP server connecting Claude to the Hospitable API v2. Supports dual transport:
- STDIO for Claude Desktop (local)
- Streamable HTTP for claude.ai custom connector (remote)
Available Tools
| Tool | Description |
|---|---|
list_properties |
List all 50+ properties with listings |
get_property |
Get details for a specific property |
search_properties |
Find available properties in a date range |
list_reservations |
List reservations with filters (requires property UUIDs) |
get_reservation |
Full reservation details with financials |
get_upcoming_checkins |
Check-ins in the next N days across all properties |
get_upcoming_checkouts |
Check-outs in the next N days across all properties |
get_calendar |
Pricing and availability calendar for a property |
update_calendar |
Update pricing/availability/min stay (prices in cents) |
list_messages |
Get guest conversation thread for a reservation |
send_message |
Send a message to a guest via booking platform |
list_reviews |
Get reviews for a property |
respond_to_review |
Post a public review response |
get_account_info |
Verify API connection / get account details |
Quick Setup
1. Get Your Hospitable PAT
- Log in to my.hospitable.com
- Go to Apps > API access > Access tokens
- Click + Add new, select Read and Write permissions
- Copy the token
2. Install
cd hospitable-mcp
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
3a. Claude Desktop (STDIO)
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"hospitable": {
"command": "/path/to/hospitable-mcp/venv/bin/python",
"args": ["/path/to/hospitable-mcp/server.py"],
"env": {
"HOSPITABLE_PAT": "your-token-here"
}
}
}
}
Restart Claude Desktop. You should see "Hospitable" in the MCP tools list.
3b. Claude.ai Custom Connector (Streamable HTTP)
Start the server in HTTP mode:
export HOSPITABLE_PAT="your-token-here"
python server.py --http --port 8000
Then in claude.ai:
- Go to Settings > Integrations (or the connectors menu)
- Add custom connector
- Enter your server URL:
http://your-server-ip:8000/mcp
For production, run behind a reverse proxy (nginx/caddy) with HTTPS.
3c. Run as a Background Service (macOS)
Create ~/Library/LaunchAgents/com.breezy.hospitable-mcp.plist:
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.breezy.hospitable-mcp</string>
<key>ProgramArguments</key>
<array>
<string>/path/to/hospitable-mcp/venv/bin/python</string>
<string>/path/to/hospitable-mcp/server.py</string>
<string>--http</string>
<string>--port</string>
<string>8000</string>
</array>
<key>EnvironmentVariables</key>
<dict>
<key>HOSPITABLE_PAT</key>
<string>your-token-here</string>
</dict>
<key>RunAtLoad</key>
<true/>
<key>KeepAlive</key>
<true/>
<key>StandardOutPath</key>
<string>/tmp/hospitable-mcp.log</string>
<key>StandardErrorPath</key>
<string>/tmp/hospitable-mcp.err</string>
</dict>
</plist>
Load it:
launchctl load ~/Library/LaunchAgents/com.breezy.hospitable-mcp.plist
Important API Notes
/reservationsendpoint REQUIRESproperties[]as a parameter. Always fetch properties first.- Calendar prices are in CENTS. $150/night = 15000.
- Message rate limits: 2/min per reservation, 50/5min global.
- Calendar update rate limit: 1000 req/min.
- Messages with no sender field are AI-generated (Hospitable automation).
- PAT tokens expire after ~1 year. Rotate at my.hospitable.com.
Combining with Other MCP Servers
Claude Desktop supports multiple MCP servers. Example config:
{
"mcpServers": {
"hospitable": {
"command": "/path/to/hospitable-mcp/venv/bin/python",
"args": ["/path/to/hospitable-mcp/server.py"],
"env": { "HOSPITABLE_PAT": "your-token" }
},
"pricelabs": {
"command": "python",
"args": ["/path/to/pricelabs-mcp/server.py"],
"env": { "PRICELABS_API_KEY": "your-key" }
}
}
}
Troubleshooting
"HOSPITABLE_PAT environment variable is not set"
- Make sure the env var is set in the Claude Desktop config or your shell
401 Unauthorized
- Your PAT may have expired. Generate a new one from my.hospitable.com
Rate limit errors (429)
- Wait and retry. The server returns rate limit details in the error.
STDIO mode works but HTTP doesn't connect from claude.ai
- Make sure your firewall allows inbound on the port
- If behind a router, set up port forwarding or use a tunnel (ngrok, Cloudflare Tunnel)
- claude.ai custom connector needs HTTPS in production
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.