Update a tracked status entry in
AI agents use memory_update_status to create or update resources in Munin Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Munin Memory environment.
This tool creates or modifies data (status entries) in a controlled, self-hosted database. It is reversible (unlike Destructive) and does not execute external code (unlike Execute). The medium severity reflects that misuse could corrupt or pollute persistent memory state across sessions, affecting agent behavior, but the impact is typically recoverable since SQLite supports standard CRUD patterns and backups.
From the tool's definition Tool name 'memory_update_status' and description indicate modification of tracked status entries in a persistent SQLite database. The 'update' verb and context of modifying stored memory state constitute a reversible write operation.
Attacks that exploit this kind of access
Update a tracked status entry in. It is categorised as a Write tool in the Munin Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_update_status: 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 Munin Memory. Nothing to install.
memory_update_status 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_status 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_status. 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_status is provided by the Munin Memory MCP server (magnus-gille/munin-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 →