AI agents call get_weekly_favorites to retrieve information from MCP RSS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves previously bookmarked articles within a time window. It performs a read-only operation with no ability to modify, delete, execute code, or affect financial systems. The blast radius of misuse is minimal—an agent could only retrieve information already marked as favorites by the user.
From the tool's definition Tool name 'get_weekly_favorites' and description 'Get favorite articles from the last 7 days' indicate a retrieval operation with no modification or side effects. Returns articles matching a filter criterion.
Attacks that exploit this kind of access
Get favorite articles from the last 7 days. Perfect for weekly review of bookmarked content. Returns articles with status=. It is categorised as a Read tool in the MCP RSS MCP Server, which means it retrieves data without modifying state.
Register the MCP RSS MCP server in PolicyLayer and add a rule for get_weekly_favorites: 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 RSS. Nothing to install.
get_weekly_favorites 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_weekly_favorites 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_weekly_favorites. 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_weekly_favorites is provided by the MCP RSS MCP server (ronnycoding/my_mcp_rss). 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 →