AI agents call get_recent_activity 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 activity history from a personal knowledge/memory system. While the description is empty, the name and context strongly suggest a read-only query. The 'medium' severity reflects that it accesses personal activity data which could be sensitive if exfiltrated by a compromised agent, but the tool itself performs no side effects.
From the tool's definition Tool name 'get_recent_activity' indicates retrieval of historical data without modification. Sibling tools like 'browsing_stats', 'commit_details', 'detected_browsers', 'git_status', 'graph_stats', and 'index_stats' are all read-only query operations.
Attacks that exploit this kind of access
get_recent_activity. 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 get_recent_activity: 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.
get_recent_activity 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 get_recent_activity 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 get_recent_activity. 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.
get_recent_activity 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 →