Housecallpro

License: MIT Python MCP

MCP server for Housecall Pro, the mid-market trades vertical SaaS (HVAC, plumbing, electrical, garage, pest, landscaping). 5 tools for AI agents to register new customers, schedule jobs, create estimates, log inbound leads, and generate invoices (env-gated) against active jobs.

As of May 2026, Housecall Pro does not ship an official MCP server. Two low-visibility community attempts exist. This is the production-quality, install-ready Python rail.

The 5 tools

Tool	Purpose	Gated?
create_pro_customer	Register a new customer in the CRM	No, safe
schedule_new_job	Schedule a new trade job for an existing customer	No, safe
create_estimate	Generate a pricing estimate or proposal	No, safe
submit_new_lead	Log a new marketing or inbound prospect lead	No, safe
generate_job_invoice	Post an official invoice against an active job	YES, HOUSECALLPRO_ALLOW_INVOICE=true required

Install

pip install housecallpro-mcp

Configure

export HOUSECALLPRO_API_KEY="your-housecallpro-api-key"
export HOUSECALLPRO_ALLOW_INVOICE="false"   # set to "true" to enable invoice creation

Get an API key in your Housecall Pro account settings. The key is sent as a Bearer token; keep it server-side.

Use with Claude Desktop

{
  "mcpServers": {
    "housecallpro": {
      "command": "housecallpro-mcp",
      "env": {
        "HOUSECALLPRO_API_KEY": "your-housecallpro-api-key",
        "HOUSECALLPRO_ALLOW_INVOICE": "false"
      }
    }
  }
}

Restart Claude Desktop. The 5 Housecall Pro tools are now available.

Use case: AI receptionist + sales agent for a trades business

Typical agent flow for inbound calls and quotes:

1. Call create_pro_customer(first_name, last_name, mobile_phone) to register the caller in CRM
2. Call schedule_new_job(customer_id, description, start_time, end_time) to book the service window
3. After the diagnostic call: create_estimate(customer_id, note) to propose pricing
4. For web-form / chat inbound: submit_new_lead(customer_id, description) to log the prospect in the sales funnel
5. (After job completion + with HOUSECALLPRO_ALLOW_INVOICE=true): generate_job_invoice(job_id) to bill the customer

Safety note

The invoice action is intentionally gated behind an explicit env var. The default install does not bill customers. Set HOUSECALLPRO_ALLOW_INVOICE="true" only when the AI agent workflow has been explicitly approved for billing actions.

Architecture

• Public MIT-licensed wrapper around the Housecall Pro REST API
• Async HTTP via httpx
• pydantic v2 input validation
• Bearer API key auth, server-side only
• Rate-limit aware (429 returns a clean error)
• Invoice action gated by env flag

Development

git clone https://github.com/NoBanks/housecallpro-mcp.git
cd housecallpro-mcp
pip install -e ".[dev]"
pytest

License

MIT. See LICENSE.

Author

Ryan Hammer (NoBanks). Solo founder + engineer. Built this and 14 other MCP servers as part of a sprint to expose AI agent rails for the products and platforms shipping daily.

• GitHub: @NoBanks
• X/Twitter: @livingagentic
• Site: livingagentic.me, nohumannearby.com

Open to AI engineering roles, contract or full-time, remote-only.