AI agents call knowledge_history to retrieve information from Loom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves revision history for a knowledge page, which is a read operation with no side effects. The description mentions 'Replace-writes snapshot the displaced' which describes how history is created (by other write operations), not what this tool does. This tool simply reads/queries the history. Low severity as it only exposes historical content.
From the tool's definition 'Body-revision history for a knowledge page' — retrieves historical revision data
Attacks that exploit this kind of access
Body-revision history for a knowledge page. Replace-writes snapshot the displaced. It is categorised as a Read tool in the Loom MCP Server, which means it retrieves data without modifying state.
Register the Loom MCP server in PolicyLayer and add a rule for knowledge_history: 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_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the knowledge_history 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_history. 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_history 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.
knowledge_history is one line of Loom's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →