AI agents call find_similar 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.
This tool searches and retrieves existing memories based on semantic similarity, analogous to a search or filter operation. It has no side effects—no data is created, modified, deleted, or executed. The blast radius of misuse is low; an agent retrieving similar memories cannot cause financial harm, destructive actions, or code execution. It is a straightforward read operation on persistent memory storage.
From the tool's definition Tool performs semantic search to 'surface memories' without modification, creation, or deletion of data. The verb 'surface' indicates retrieval/query operation.
Attacks that exploit this kind of access
Surface memories semantically near an existing ref or free-form text. 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 find_similar: 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.
find_similar 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 find_similar 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 find_similar. 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.
find_similar 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 →