Update an existing mandatory or forbidden rule by its id.
AI agents use memory_update_rule to create or update resources in Claude Memory MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Memory MCP environment.
This tool modifies rules that enforce constraints on memory operations within a project context. While it creates side effects by changing rule behavior, the change is reversible (a rule can be updated again). This places it in the Write category rather than Execute or Destructive.
From the tool's definition The tool description states 'Update an existing mandatory or forbidden rule by its id.' The verb 'Update' indicates modification of existing data (rules) without deletion or irreversible destruction.
Attacks that exploit this kind of access
Update an existing mandatory or forbidden rule by its id. It is categorised as a Write tool in the Claude Memory MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Memory MCP server in PolicyLayer and add a rule for memory_update_rule: 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 Claude Memory MCP. Nothing to install.
memory_update_rule 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_update_rule 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_update_rule. 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_update_rule is provided by the Claude Memory MCP server (navid-kianfar/claude-memory-mcp). 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 →