Add a URL to the library for text-to-speech reading.
AI agents use add_url to create or update resources in Mcp Elevenreader — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Elevenreader environment.
This tool creates a new document/resource entry in the ElevenReader library by accepting a URL. It is reversible (the entry can be deleted via sibling tool 'delete_read'), produces no external side effects beyond storage, and does not execute arbitrary code or access financial systems.
From the tool's definition Tool name 'add_url' and description 'Add a URL to the library for text-to-speech reading' indicate creation of a new library entry. The verb 'Add' combined with the action of importing a URL into the system constitutes data creation.
Attacks that exploit this kind of access
Add a URL to the library for text-to-speech reading. It is categorised as a Write tool in the Mcp Elevenreader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Elevenreader MCP server in PolicyLayer and add a rule for add_url: 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.
add_url is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_url 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 add_url. 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.
add_url 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 →