AI agents use manage_tags to create or update resources in Inoreader — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Inoreader environment.
This tool modifies article states and metadata (read/unread status, starred status, custom tags) but does not irreversibly delete data or execute arbitrary code. These changes are reversible through subsequent calls to unmark, unstar, or remove tags.
From the tool's definition Tool description states 'Mark articles as read/unread/starred, or apply/remove custom tags' - these are state modifications that change article metadata. The 'add_tag=' parameter indicates tag application capability, a reversible write operation.
Attacks that exploit this kind of access
Mark articles as read/unread/starred, or apply/remove custom tags. To mark as read: add_tag=. It is categorised as a Write tool in the Inoreader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Inoreader MCP server in PolicyLayer and add a rule for manage_tags: 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.
manage_tags 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 manage_tags 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 manage_tags. 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.
manage_tags 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 →