Trigger: User wants to MODIFY/UPDATE memories, OR as the final step of a DELETION workflow. Purpose: Modify existing memories or record deletion feedback. STRICT RULES: 1. MODIFICATION: Use this tool directly for soft updates/corrections. 2. DELETION: Use this tool AFTER calling \
AI agents use add_feedback to create or update resources in MemOS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MemOS environment.
This tool creates or modifies data reversibly. It updates existing memories (a Write operation) and records deletion feedback, which is also a form of data modification. While it's part of a deletion workflow, the tool itself does not perform irreversible deletion—that's handled by other tools like delete_memory.
From the tool's definition Tool description explicitly states it is used to 'MODIFY/UPDATE memories' and 'record deletion feedback.' The trigger indicates it modifies existing memories or records feedback about deletions.
Documented attack patterns abuse exactly the kind of access add_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MemOS, and nothing reaches the server without passing your rules. This is the rule we recommend for add_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"add_feedback": {
"limits": [
{
"counter": "add_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_feedback stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Trigger: User wants to MODIFY/UPDATE memories, OR as the final step of a DELETION workflow. Purpose: Modify existing memories or record deletion feedback. STRICT RULES: 1. MODIFICATION: Use this tool directly for soft updates/corrections. 2. DELETION: Use this tool AFTER calling \. It is categorised as a Write tool in the MemOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MemOS MCP server in PolicyLayer and add a rule for add_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 MemOS. Nothing to install.
add_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 add_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 add_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.
add_feedback is provided by the MemOS MCP server (memtensor/memos-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MemOS, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 MemOS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.