Find a Folder by Short Prefix (e.g. REQ, LLR, TST)
AI agents call find_document to retrieve information from Doorstop MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (locating documents by prefix) without creating, modifying, deleting, or executing operations. It is a straightforward read operation typical of requirements management systems. Low severity due to minimal blast radius—misuse would only return unexpected document results without data loss or external side effects.
From the tool's definition Tool name 'find_document' and description 'Find a Folder by Short Prefix' indicate a search/query operation with no modification or side effects.
Attacks that exploit this kind of access
Find a Folder by Short Prefix (e.g. REQ, LLR, TST). It is categorised as a Read tool in the Doorstop MCP MCP Server, which means it retrieves data without modifying state.
Register the Doorstop MCP server in PolicyLayer and add a rule for find_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 Doorstop MCP. Nothing to install.
find_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 find_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 find_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.
find_document is provided by the Doorstop MCP server (jannled/doorstopmcp). 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 →