AI agents call ask_ai_about_documents 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.
This tool retrieves and analyzes data from DEVONthink documents without creating, modifying, or deleting records. The AI analysis is performed on document content for informational purposes only. There are no side effects, state changes, or irreversible actions. The blast radius of misuse is minimal — an agent could only retrieve information it already has access to.
From the tool's definition Tool performs 'Ask AI questions about specific DEVONthink documents for analysis, comparison, or extraction' — these are query and analysis operations with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Ask AI questions about specific DEVONthink documents for analysis, comparison, or extraction. 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 ask_ai_about_documents: 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.
ask_ai_about_documents 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 ask_ai_about_documents 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 ask_ai_about_documents. 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.
ask_ai_about_documents 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 →