AI agents use update_memory to create or update resources in Memory-Plus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memory-Plus environment.
update_memory modifies data (memories) reversibly within the RAG store. This is a Write operation rather than Read (which would be retrieve/get_recent_memories), Execute (no code execution), Destructive (modifications are reversible, unlike the sibling delete_memory), or Financial (no monetary impact).
From the tool's definition Tool name 'update_memory' combined with server description stating the system 'enables recording, retrieval, updating, and visualization of persistent memories'.
Documented attack patterns abuse exactly the kind of access update_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory-Plus, and nothing reaches the server without passing your rules. This is the rule we recommend for update_memory:
{
"version": "1",
"default": "deny",
"tools": {
"update_memory": {
"limits": [
{
"counter": "update_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_memory 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.
update_memory. It is categorised as a Write tool in the Memory-Plus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memory-Plus MCP server in PolicyLayer and add a rule for update_memory: 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 Memory-Plus. Nothing to install.
update_memory 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 update_memory 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 update_memory. 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.
update_memory is provided by the Memory-Plus MCP server (yuchen20/memory-plus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Memory-Plus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Memory-Plus tools catalogued and risk-classified — across an index of 42,500+ MCP servers.