Search installed site adapters by name, description, or domain. Pass domain to filter by the current page
AI agents call site_search to retrieve information from Ma Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information about available site adapters without creating, modifying, deleting, or executing any operations. It is a simple search/filter function that returns metadata about adapters.
From the tool's definition Tool performs a search operation on installed site adapters by name, description, or domain. The description indicates it 'Search installed site adapters' which is a query/retrieval operation with no modification or execution of external actions.
Attacks that exploit this kind of access
Search installed site adapters by name, description, or domain. Pass domain to filter by the current page. It is categorised as a Read tool in the Ma Browser MCP Server, which means it retrieves data without modifying state.
Register the Ma Browser MCP server in PolicyLayer and add a rule for site_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 Ma Browser. Nothing to install.
site_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 site_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 site_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.
site_search is provided by the Ma Browser MCP server (zzhan111/multi-agents-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →