Update an existing memory in-place without losing metadata.
AI agents use update to create or update resources in Nexus Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nexus Memory environment.
This tool creates or modifies data within the persistent memory store. While 'update' is reversible (a user could update again or use 'forget' to remove), it directly alters stored information that other agents may depend on. The 'anti-poisoning features' mentioned in the server description suggest the system recognizes risks from malicious memory updates.
From the tool's definition 'Update an existing memory in-place without losing metadata' — modifies stored data reversibly. The tool changes memory content while preserving metadata, a classic write operation.
Attacks that exploit this kind of access
Update an existing memory in-place without losing metadata. It is categorised as a Write tool in the Nexus Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nexus Memory MCP server in PolicyLayer and add a rule for update: 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 Nexus Memory. Nothing to install.
update 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 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. 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 is provided by the Nexus Memory MCP server (neboy72/nexus-memory). 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 →