AI agents invoke memory_maintenance to trigger actions in Exocortex. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool runs backend operations that modify system state (importance adjustments, archival actions) and supports conditional execution via flags. These are neither simple reads nor reversible writes, but rather administrative operations whose side effects depend on argument configuration. The term 'maintenance' and mention of 'optional operations' confirm this is Execute-class.
From the tool's definition Tool performs 'maintenance tasks' including 'importance adjustment, archival, health checks' and accepts 'boolean flags' for 'optional operations' — indicating it executes procedural operations with configurable effects on the memory system.
Attacks that exploit this kind of access
Run maintenance tasks: importance adjustment, archival, health checks, and optional operations via boolean flags. It is categorised as a Execute tool in the Exocortex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_maintenance: 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 Exocortex. Nothing to install.
memory_maintenance is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the memory_maintenance 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_maintenance. 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_maintenance is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →