AI agents call reader_list_documents to retrieve information from Reader MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates documents from a user's Readwise Reader library without modifying or deleting data. Listing documents is a non-destructive query operation. Even in a compromised scenario, an AI agent could only discover what documents exist in the knowledge repository, not alter or delete them.
From the tool's definition Tool name 'reader_list_documents' indicates a query/listing operation. Server description explicitly states the server allows clients to 'list, retrieve, and update documents', positioning list as a read operation with no side effects.
Documented attack patterns abuse exactly the kind of access reader_list_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Reader MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for reader_list_documents:
{
"version": "1",
"default": "deny",
"tools": {
"reader_list_documents": {}
}
}reader_list_documents 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.
reader_list_documents. It is categorised as a Read tool in the Reader MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Reader MCP Server MCP server in PolicyLayer and add a rule for reader_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 Reader MCP Server. Nothing to install.
reader_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 reader_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 reader_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.
reader_list_documents is provided by the Reader MCP Server MCP server (xinthink/reader-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Reader MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Reader MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.