Get full reading history — all books in compact format (title, author, progress, language).
AI agents call list_all_reads to retrieve information from Mcp Elevenreader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns reading history and document metadata (title, author, progress, language) without altering any data. It performs a passive read operation. The scope is limited to retrieving user's own reading history, making the blast radius minimal even if misused by an AI agent.
From the tool's definition Tool name 'list_all_reads' and description 'Get full reading history — all books in compact format' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get full reading history — all books in compact format (title, author, progress, language). It is categorised as a Read tool in the Mcp Elevenreader MCP Server, which means it retrieves data without modifying state.
Register the Mcp Elevenreader MCP server in PolicyLayer and add a rule for list_all_reads: 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 Mcp Elevenreader. Nothing to install.
list_all_reads 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_all_reads 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_all_reads. 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_all_reads is provided by the Mcp Elevenreader MCP server (mit9/mcp-elevenreader). 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 →