Get dashboard stats: total feeds, unread count, entries per category.
AI agents call get_stats_tool to retrieve information from MCP Feed Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and aggregates existing data (counts and statistics) from the SQLite backend without creating, modifying, deleting, or executing any state-changing operations. It is a read-only retrieval function with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states it retrieves dashboard stats including 'total feeds, unread count, entries per category' — purely informational aggregation with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get dashboard stats: total feeds, unread count, entries per category. It is categorised as a Read tool in the MCP Feed Reader MCP Server, which means it retrieves data without modifying state.
Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for get_stats_tool: 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 Feed Reader. Nothing to install.
get_stats_tool 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_stats_tool 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_stats_tool. 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_stats_tool is provided by the MCP Feed Reader MCP server (pypi:mcp-feed-reader-crunchtools). 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 →