AI agents use create_summary_document 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 performs a reversible write operation—it creates new summary documents in the DEVONthink database. While the summaries are AI-generated transformations of existing content, the core action is document creation (a Write operation), not mere querying (Read).
From the tool's definition The tool 'create_summary_document' creates a new document artifact in DEVONthink by generating and persisting AI-summarized content from existing documents. This is explicitly a creation operation that adds new data to the database.
Attacks that exploit this kind of access
Create an AI-generated summary document from multiple DEVONthink documents. 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_summary_document: 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_summary_document 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_summary_document 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_summary_document. 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_summary_document 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 →