AI agents call recent_browsing_history 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 historical browsing data without modifying, deleting, or executing anything. Even if it exposes sensitive personal information, the action itself is read-only. Severity is low because while browsing history can be sensitive, retrieval alone has minimal blast radius compared to write/execute/destructive operations.
From the tool's definition Tool name 'recent_browsing_history' indicates retrieval of browsing history data. Description is empty, but name and server context (semantic search over personal data) suggest a query/fetch operation with no side effects.
Attacks that exploit this kind of access
recent_browsing_history. 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 recent_browsing_history: 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.
recent_browsing_history 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 recent_browsing_history 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 recent_browsing_history. 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.
recent_browsing_history 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 →