AI agents use knowledge_write 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.
The tool creates or modifies entity pages (Write operation) rather than permanently deleting them. While 'REPLACES' suggests overwriting, the operation is reversible—the previous state could theoretically be recovered or the page modified again. This is distinct from Destructive operations which are irreversible.
From the tool's definition Tool description states 'Upsert an entity page by slug' and 'body REPLACES by default', indicating reversible creation or modification of data.
Attacks that exploit this kind of access
Upsert an entity page by slug. On an existing slug: body REPLACES by default. 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_write: 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_write 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_write 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_write. 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_write 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 →