AI agents use mem0_send_feedback to create or update resources in Mem0 MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mem0 MCP Server environment.
The tool appears to create or record feedback data within a persistent memory system. Without a description, confidence is reduced, but the naming pattern and server context strongly suggest a Write operation (data creation/modification) rather than Read (which would be 'get_feedback'), Destructive (no indication of deletion), or other categories.
From the tool's definition Tool name contains 'send_feedback' which implies modifying or recording feedback data. The Mem0 server is described as a persistent memory system that allows storing, retrieving, and managing memories.
Documented attack patterns abuse exactly the kind of access mem0_send_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mem0 MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mem0_send_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"mem0_send_feedback": {
"limits": [
{
"counter": "mem0_send_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mem0_send_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.
mem0_send_feedback. It is categorised as a Write tool in the Mem0 MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mem0 MCP Server MCP server in PolicyLayer and add a rule for mem0_send_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 Mem0 MCP Server. Nothing to install.
mem0_send_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 mem0_send_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 mem0_send_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.
mem0_send_feedback is provided by the Mem0 MCP Server MCP server (ryaker/mcp-mem0-general). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mem0 MCP Server, 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.
18 Mem0 MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.