Set article tag, status has only two values: normal, favorite, articleId is article id
AI agents use set_tag to create or update resources in MCP RSS Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP RSS Server environment.
This tool modifies article metadata (tags and status) in a reversible manner without deleting data or executing code. The changes can be undone by setting different tag/status values. The blast radius is minimal—limited to local article state management within the RSS feed reader context, with no external side effects, financial impact, or destructive capability.
From the tool's definition Tool description states "Set article tag" and "status has only two values: normal, favorite", indicating modification of article metadata attributes.
Attacks that exploit this kind of access
Set article tag, status has only two values: normal, favorite, articleId is article id. It is categorised as a Write tool in the MCP RSS Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP RSS Server MCP server in PolicyLayer and add a rule for set_tag: 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 Server. Nothing to install.
set_tag 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_tag 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_tag. 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_tag is provided by the MCP RSS Server MCP server (xrusjohn/mcp_rss_buhe). 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 →