Retrieve document by ID with complete content. WHEN: You need the full document content and metadata for a specific document. Common after listing documents or when a memory references a document ID. BEHAVIOR: Returns complete document including full content, description, and metadata. Ownership ...
AI agents call get_document to retrieve information from Forgetful without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing data from a knowledge base storage system. It performs a read-only query operation with no side effects—no data is created, modified, deleted, or executed. The explicit instruction 'NOT-USE: For browsing multiple documents' confirms it is a simple retrieval function. The ownership verification mentioned is a safety control, not a capability that elevates the risk category.
From the tool's definition Tool name is 'get_document' and description states it will 'Retrieve document by ID with complete content' and 'Returns complete document including full content, description, and metadata.' No modification, deletion, or execution capabilities are mentioned.
Documented attack patterns abuse exactly the kind of access get_document gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgetful, and nothing reaches the server without passing your rules. This is the rule we recommend for get_document:
{
"version": "1",
"default": "deny",
"tools": {
"get_document": {}
}
}get_document is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve document by ID with complete content. WHEN: You need the full document content and metadata for a specific document. Common after listing documents or when a memory references a document ID. BEHAVIOR: Returns complete document including full content, description, and metadata. Ownership verified automatically. NOT-USE: For browsing multiple documents (use list_documents). Args: document_id: Unique document ID ctx: Context (automatically injected) Returns: Complete Document with content, description, metadata Raises: ToolError if document not found or access denied. It is categorised as a Read tool in the Forgetful MCP Server, which means it retrieves data without modifying state.
Register the Forgetful MCP server in PolicyLayer and add a rule for get_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 Forgetful. Nothing to install.
get_document 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_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 get_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.
get_document is provided by the Forgetful MCP server (scottrbk/forgetful). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
59 Forgetful tools catalogued and risk-classified — across an index of 42,500+ MCP servers.