Get AI-powered suggestions for pruning old or low-importance conversations
AI agents call memory_prune to retrieve information from Sekha MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it queries existing memory data and returns analyzed suggestions without modifying, deleting, or executing actions on the underlying data. The actual deletion would require a separate destructive operation. The severity is low because misuse would only affect data visibility/recommendations, not cause irreversible loss.
From the tool's definition The tool description states it 'Get[s] AI-powered suggestions for pruning old or low-importance conversations'. The word 'suggestions' indicates the tool retrieves recommendations rather than executing deletions.
Attacks that exploit this kind of access
Get AI-powered suggestions for pruning old or low-importance conversations. It is categorised as a Read tool in the Sekha MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sekha MCP Server MCP server in PolicyLayer and add a rule for memory_prune: 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 Sekha MCP Server. Nothing to install.
memory_prune 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 memory_prune 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 memory_prune. 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.
memory_prune is provided by the Sekha MCP Server MCP server (sekha-ai/sekha-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 →