AI agents use knowledge_archive to create or update resources in Loom — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Loom environment.
This tool modifies data (knowledge page status) but does so reversibly. 'Soft-retire' implies the archival is not destructive — the page is not deleted, only marked inactive. An agent could archive critical memory pages erroneously, disrupting agent cognition and continuity, but the action can be undone (e.g., by un-archiving).
From the tool's definition 'Soft-retire a knowledge page: set its status to archived with an optional tombstone note' — modifies the status field of a knowledge page to 'archived' and optionally adds metadata (tombstone note).
Attacks that exploit this kind of access
Soft-retire a knowledge page: set its status to archived with an optional tombstone note. It is categorised as a Write tool in the Loom MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Loom MCP server in PolicyLayer and add a rule for knowledge_archive: 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 Loom. Nothing to install.
knowledge_archive 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 knowledge_archive 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 knowledge_archive. 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.
knowledge_archive is provided by the Loom MCP server (jbarket/loom). 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 →