zillow_search
Search Zillow listings. Returns normalized Zillow public listing search results. Callers must pass complete map bounds from autocomplete when available, or a region id fallback.
This record as markdown: /tools/crawlora-mcp/zillow-search.md
What zillow_search does on Crawlora
AI agents call zillow_search to retrieve information from Crawlora without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
east | number | — | Map east bound from autocomplete |
page | integer | — | 1-based page |
west | number | — | Map west bound from autocomplete |
north | number | — | Map north bound from autocomplete |
south | number | — | Map south bound from autocomplete |
status | string | — | Search context: for_sale, for_rent, or sold |
location | string | Yes | Display location |
region_id | integer | — | Zillow region id from autocomplete, used when complete bounds are not provided |
region_type | integer | — | Zillow region type from autocomplete, used with region_id fallback |
Parameters from the server's own tool schema.
Why zillow_search is rated Low
Even though zillow_search only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs zillow_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crawlora, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For zillow_search, this is the rule to start with:
zillow_search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crawlora, apply this rule, and every zillow_search call is checked against it from then on.
Questions about zillow_search
Search Zillow listings. Returns normalized Zillow public listing search results. Callers must pass complete map bounds from autocomplete when available, or a region id fallback. It is categorised as a Read tool in the Crawlora MCP Server, which means it retrieves data without modifying state.
zillow_search accepts 9 parameters: east, page, west, north, south, status, location, region_id, region_type. Required: location. The full parameter table on this page comes from the server's own tool schema.
Register the Crawlora MCP server in PolicyLayer and add a rule for zillow_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crawlora. Nothing to install.
zillow_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the zillow_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for zillow_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
zillow_search is provided by the Crawlora MCP server (crawlora-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crawlora, and thousands of servers like it.
This server
Across the catalogue