Writes new plain text content to an existing document. The UUID must already be in the binder (use add_document to create a new document). The call will fail with a clear error if Scrivener has the project open — close Scrivener first.
AI agents use write_document to create or update resources in Scrivener — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scrivener environment.
This tool creates or modifies document content reversibly within a Scrivener project. While it modifies data, the changes can be undone (typical for document editors) and do not irreversibly delete data. The requirement that the UUID already exist and documents be created separately (via add_document) means this strictly performs write operations on existing content.
From the tool's definition Tool description states it 'Writes new plain text content to an existing document', which is a create/modify operation. The description explicitly indicates content modification without deletion or data destruction.
Attacks that exploit this kind of access
Writes new plain text content to an existing document. The UUID must already be in the binder (use add_document to create a new document). The call will fail with a clear error if Scrivener has the project open — close Scrivener first. It is categorised as a Write tool in the Scrivener MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scrivener MCP server in PolicyLayer and add a rule for write_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 Scrivener. Nothing to install.
write_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 write_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 write_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.
write_document is provided by the Scrivener MCP server (sschmitt-cg/scrivener-mcp). 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 →