Get adapter metadata including args, example, and domain
AI agents call site_info 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 and queries metadata about site adapters (arguments, examples, domain information). It has no side effects—it simply returns information about available adapters. This is a classic Read operation. While the parent server has broad browser access capabilities, this specific tool is narrowly scoped to metadata retrieval, making it low severity.
From the tool's definition Tool name 'site_info' and description 'Get adapter metadata including args, example, and domain' indicate retrieval of metadata only. No modification, deletion, or execution of external actions occurs.
Attacks that exploit this kind of access
Get adapter metadata including args, example, and domain. 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_info: 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_info 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_info 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_info. 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_info 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 →