recall_changed_since
AI agents call recall_changed_since to retrieve information from Memanto MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'recall' prefix across sibling tools strongly suggests this is a query/retrieval operation. The suffix 'changed_since' indicates a filtered read of historical changes rather than modification or deletion. Without explicit evidence of side effects, this classifies as Read. Confidence is moderate (0.8) rather than high because the description is empty, leaving some ambiguity about edge cases.
From the tool's definition Tool name 'recall_changed_since' indicates retrieval of data (recall) with a time-based filter; no description provided, but naming pattern is consistent with read operations on sibling tools like 'recall', 'recall_recent', and 'recall_as_of' which all access…
Attacks that exploit this kind of access
recall_changed_since. It is categorised as a Read tool in the Memanto MCP MCP Server, which means it retrieves data without modifying state.
Register the Memanto MCP server in PolicyLayer and add a rule for recall_changed_since: 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 Memanto MCP. Nothing to install.
recall_changed_since 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 recall_changed_since 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 recall_changed_since. 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.
recall_changed_since is provided by the Memanto MCP server (moorcheh-ai/memanto). 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 →