brand_retrieve
Retrieve brand data by domain. Fetches a domain's homepage and Web App Manifest and extracts a normalized brand profile (title, description, brand colors normalized to hex, logos and icons ranked best-first, backdrops, socials, links, and any schema.org organization data). Enrichment-only fields ...
This record as markdown: /tools/crawlora-mcp/brand-retrieve.md
What brand_retrieve does on Crawlora
AI agents call brand_retrieve 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 |
|---|---|---|---|
domain | string | Yes | Domain to retrieve brand data for, e.g. context.dev |
maxAgeMs | integer | — | Cache freshness window in milliseconds, clamps to 1 day..1 year |
maxSpeed | boolean | — | Optimize for speed by skipping schema.org and footer-link extraction |
timeoutMS | integer | — | Upstream fetch timeout in milliseconds, clamps to 1000..300000 |
force_language | string | — | Accepted for compatibility; not applied in HTML-only mode |
Parameters from the server's own tool schema.
Why brand_retrieve is rated Low
Even though brand_retrieve 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 brand_retrieve 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 brand_retrieve, this is the rule to start with:
brand_retrieve 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 brand_retrieve call is checked against it from then on.
Questions about brand_retrieve
Retrieve brand data by domain. Fetches a domain's homepage and Web App Manifest and extracts a normalized brand profile (title, description, brand colors normalized to hex, logos and icons ranked best-first, backdrops, socials, links, and any schema.org organization data). Enrichment-only fields that are not present in the page markup are returned as null. It is categorised as a Read tool in the Crawlora MCP Server, which means it retrieves data without modifying state.
brand_retrieve accepts 5 parameters: domain, maxAgeMs, maxSpeed, timeoutMS, force_language. Required: domain. 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 brand_retrieve: 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.
brand_retrieve 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 brand_retrieve 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 brand_retrieve. 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.
brand_retrieve 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