AI agents call browsing_stats to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns statistical information about browsing activity. It performs no side effects, creates no data, executes no commands, and causes no destructive or financial operations. It is purely informational/diagnostic in nature, making it a Read category tool. Severity is low because browsing statistics are typically non-sensitive aggregate data with limited blast radius if misused by an agent.
From the tool's definition Tool name 'browsing_stats' and description 'Get overall browsing statistics from all detected browsers' indicate a query operation that retrieves aggregated data without modification.
Attacks that exploit this kind of access
Get overall browsing statistics from all detected browsers. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for browsing_stats: 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 Memory. Nothing to install.
browsing_stats 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 browsing_stats 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 browsing_stats. 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.
browsing_stats is provided by the Memory MCP server (shaktisinhchavda/memory-mcp). 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 →