AI agents use create_from_url 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.
This tool creates new records in DEVONthink, a reversible operation that modifies the database state. It is a Write operation, not Read (no side effects) or Destructive (reversible). Severity is medium because creating unwanted records could clutter the database and consume resources, but the operation can be undone via delete_record. No financial or destructive consequences from the creation alone.
From the tool's definition Tool name 'create_from_url' and description 'Create a record in DEVONthink from a web URL' explicitly indicate creation of new data.
Attacks that exploit this kind of access
Create a record in DEVONthink from a web URL. 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 create_from_url: 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.
create_from_url 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 create_from_url 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 create_from_url. 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.
create_from_url 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 →