AI agents use add_tags to create or update resources in Devon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Devon environment.
Adding tags is a metadata modification that changes record properties reversibly. It does not execute code, delete data, or move money, placing it in the Write category. Severity is medium because tag manipulation could affect record organization and searchability, but the change is easily reversible and has limited blast radius compared to destructive operations.
From the tool's definition Tool description states 'Adds tags to a DEVONthink record.' This is a create/modify operation that reversibly alters metadata on an existing record without deleting or overwriting the original content.
Attacks that exploit this kind of access
Adds tags to a DEVONthink record. It is categorised as a Write tool in the Devon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Devon MCP server in PolicyLayer and add a rule for add_tags: 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.
add_tags 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 add_tags 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 add_tags. 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.
add_tags 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 →