AI agents call compare to retrieve information from Devon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The compare operation retrieves and analyzes existing records to identify similarities. It has no side effects, creates no new data, and cannot modify or delete records. This is a read-only analytical operation with minimal risk if misused by an AI agent, as it only returns comparative analysis without affecting the underlying data store.
From the tool's definition Tool name is 'compare' and description states it 'Compare DEVONthink records for similarities' — this is a retrieval and analysis operation that reads data without modifying, creating, or deleting any records.
Attacks that exploit this kind of access
Compare DEVONthink records for similarities. It is categorised as a Read tool in the Devon MCP Server, which means it retrieves data without modifying state.
Register the Devon MCP server in PolicyLayer and add a rule for compare: 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 Devon. Nothing to install.
compare 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 compare 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 compare. 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.
compare is provided by the Devon MCP server (mnott/devon). 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 →