Mark a blog/feed as favorite or remove from favorites. Favorite blogs appear first in get_sources and can be prioritized/filtered in get_content/search_articles. Use to: highlight preferred blogs, create reading priorities, filter by favorites. Get feed IDs from get_sources first. Workflow: (1) g...
AI agents use set_favorite_blog to create or update resources in MCP RSS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP RSS environment.
set_favorite_blog creates or modifies user preference metadata (favorite status) which is a Write operation—reversible configuration of the reading interface. It has no Read-only characteristics (it modifies state), is not Destructive (favorites can be unmarked), does not Execute arbitrary code, and has no Financial implications.
From the tool's definition Tool description explicitly states it marks a blog/feed as favorite or removes from favorites, modifying metadata about feed preferences.
Attacks that exploit this kind of access
Mark a blog/feed as favorite or remove from favorites. Favorite blogs appear first in get_sources and can be prioritized/filtered in get_content/search_articles. Use to: highlight preferred blogs, create reading priorities, filter by favorites. Get feed IDs from get_sources first. Workflow: (1) get_sources to find feed ID, (2) set_favorite_blog to mark it, (3) use favoriteBlogsOnly or prioritizeFavoriteBlogs filters. It is categorised as a Write tool in the MCP RSS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP RSS MCP server in PolicyLayer and add a rule for set_favorite_blog: 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.
set_favorite_blog 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 set_favorite_blog 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 set_favorite_blog. 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.
set_favorite_blog 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 →