What is required to run the server?
Node.js 18+ and an ATTOM API key. Optionally, a Google Maps API key for address normalization.
@jmclaughlin724
Basic information
No overview available yet
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The ATTOM MCP Server is a Model Context Protocol server that surfaces the ATTOM Data property dataset to AI agents and traditional applications. It is written in TypeScript with ES modules and supports both HTTP and stdio transports, fallback strategies, automatic retries, and development tooling.
Install via git clone and npm ci, configure environment variables (ATTOM_API_KEY required), then launch using npm run mcp:http or npm run mcp:stdio. Interact via the attom_query MCP tool, specifying a kind endpoint key and params object.
include0SalesAmounts, includeFullSalesOnly, onlyPropertiesWithPool).Node.js 18+ and an ATTOM API key. Optionally, a Google Maps API key for address normalization.
Yes. Use `npm run mcp:http` for HTTP transport and `npm run mcp:stdio` for stdio transport. Both expose the same MCP interface.
If ATTOM returns "Unable to locate a property record" on the first attempt, the server widens the sqFeetRange by 30% and sets yearBuiltRange to 40 years, then retries once.
Data is cached in an in-memory TTL map (default 3600 seconds). The cache adapter can be swapped for Redis or Memcached.
Authentication uses an ATTOM API key set in the `ATTOM_API_KEY` environment variable. No OAuth or other auth is described.
A curated list of references for MLOps
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
🚀 The fast, Pythonic way to build MCP servers and clients.

Model Context Protocol Servers

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments