Batch version of get_document. Returns metadata and plain text content for many documents in a single call. Use this when you need the prose for several specific documents (e.g. the previous three scenes for continuity, or every Text item with a particular label). Cheaper than calling get_documen...
AI agents call get_documents to retrieve information from Scrivener without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries document content from Scrivener projects without modifying, creating, or deleting any data. It is a batch optimization of get_document for efficiency. The blast radius of misuse is limited to unauthorized information disclosure of existing project content, which is a confidentiality concern but not destructive or executable in nature.
From the tool's definition Tool name is 'get_documents' and description states it 'Returns metadata and plain text content for many documents in a single call.' The verb 'Returns' and the absence of any modification, creation, or deletion language clearly indicate a read-only retrieval…
Attacks that exploit this kind of access
Batch version of get_document. Returns metadata and plain text content for many documents in a single call. Use this when you need the prose for several specific documents (e.g. the previous three scenes for continuity, or every Text item with a particular label). Cheaper than calling get_document repeatedly. Items not found are returned with an. It is categorised as a Read tool in the Scrivener MCP Server, which means it retrieves data without modifying state.
Register the Scrivener MCP server in PolicyLayer and add a rule for get_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 Scrivener. Nothing to install.
get_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 get_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 get_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.
get_documents 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 →