Unfollow a list to stop seeing its posts in the timeline.
AI agents use unfollowList to create or update resources in Xdevplatform/xmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xdevplatform/xmcp environment.
Unfollowing a list modifies the user's subscription/follow state but is reversible (the user can re-follow the list). No data is permanently deleted, making this a Write rather than Destructive action. Blast radius is low as it only affects the authenticated user's timeline preferences.
From the tool's definition Unfollow a list to stop seeing its posts in the timeline
Attacks that exploit this kind of access
Unfollow a list to stop seeing its posts in the timeline. It is categorised as a Write tool in the Xdevplatform/xmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xdevplatform/x MCP server in PolicyLayer and add a rule for unfollowList: 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 Xdevplatform/xmcp. Nothing to install.
unfollowList 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 unfollowList 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 unfollowList. 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.
unfollowList is provided by the Xdevplatform/x MCP server (xdevplatform/xmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
unfollowList is one line of Xdevplatform/x's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →