AI agents call get_unread_counts to retrieve information from Inoreader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries unread counts—a read-only operation that does not create, modify, delete, or execute code. It has negligible blast radius as it merely returns informational metrics about the user's RSS feeds.
From the tool's definition Tool name 'get_unread_counts' and description 'Get unread article counts for all feeds and folders' indicates data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get unread article counts for all feeds and folders, sorted by count descending. Use this first to understand what needs attention. Costs 1 Zone 1 request. It is categorised as a Read tool in the Inoreader MCP Server, which means it retrieves data without modifying state.
Register the Inoreader MCP server in PolicyLayer and add a rule for get_unread_counts: 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 Inoreader. Nothing to install.
get_unread_counts 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 get_unread_counts 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 get_unread_counts. 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.
get_unread_counts is provided by the Inoreader MCP server (justmytwospence/inoreader-mcp). 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 →