Record explicit retrieval-quality feedback: a specific memory was perfectly relevant / wrongly retrieved / outdated / etc for a specific query. Distinct from memory_correct (which fixes content). Use this when a retrieved memory
AI agents use memory_feedback to create or update resources in Exocortex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Exocortex environment.
This tool creates/writes feedback records tied to specific memories and queries, flagging relevance, incorrectness, or staleness. It does not delete or overwrite the underlying memory content (that's memory_correct), nor does it execute code or move money. It's a reversible write operation with low blast radius — misuse at worst degrades retrieval tuning quality.
From the tool's definition 'Record explicit retrieval-quality feedback' and 'Distinct from memory_correct (which fixes content)' — the tool writes feedback metadata about retrieval quality without modifying the memory content itself.
Attacks that exploit this kind of access
Record explicit retrieval-quality feedback: a specific memory was perfectly relevant / wrongly retrieved / outdated / etc for a specific query. Distinct from memory_correct (which fixes content). Use this when a retrieved memory. It is categorised as a Write tool in the Exocortex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_feedback: 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_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memory_feedback 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_feedback. 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_feedback 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 →