AI agents call list_documents to retrieve information from Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves metadata about existing documents in the local knowledge base without modifying, deleting, or executing any operations. It is purely informational and falls under the Read category. The severity is low because listing documents poses minimal risk—it only exposes information about document inventory without enabling data manipulation or execution of arbitrary operations.
From the tool's definition Tool name 'list_documents' and description indicate it returns a list of registered documents (登録済みドキュメントの一覧を返します = 'returns a list of registered documents'). This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
登録済みドキュメントの一覧を返します。. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Local Rag MCP server in PolicyLayer and add a rule for list_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 Local Rag. Nothing to install.
list_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 list_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 list_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.
list_documents is provided by the Local Rag MCP server (n-irei/local-rag-mcp-server). 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 →