brave_search
Search Brave. Returns normalized web search results from Brave Search for a query string, along with offset-based pagination, related queries, discussions, videos, and the right-side knowledge card when Brave includes one. Use time_range for preset ranges or date_from/date_to for a custom YYYY-MM...
This record as markdown: /tools/crawlora-mcp/brave-search.md
What brave_search does on Crawlora
AI agents call brave_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 |
|---|---|---|---|
q | string | Yes | Search query |
lang | string | — | Brave UI language; defaults to en-us |
offset | integer | — | Zero-based Brave result page |
country | string | — | Brave result country; defaults to us |
date_to | string | — | Custom end date in YYYY-MM-DD; requires date_from |
date_from | string | — | Custom start date in YYYY-MM-DD; requires date_to |
time_range | string | — | Preset time filter: any, day, week, month, year, or custom |
Parameters from the server's own tool schema.
Why brave_search is rated Low
Even though brave_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 brave_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 brave_search, this is the rule to start with:
brave_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 brave_search call is checked against it from then on.
Questions about brave_search
Search Brave. Returns normalized web search results from Brave Search for a query string, along with offset-based pagination, related queries, discussions, videos, and the right-side knowledge card when Brave includes one. Use time_range for preset ranges or date_from/date_to for a custom YYYY-MM-DD range. Locale defaults to country=us and lang=en-us. It is categorised as a Read tool in the Crawlora MCP Server, which means it retrieves data without modifying state.
brave_search accepts 7 parameters: q, lang, offset, country, date_to, date_from, time_range. Required: q. 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 brave_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.
brave_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 brave_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 brave_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.
brave_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