AI agents use unfollow_artists_or_users to create or update resources in PersonalizationMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PersonalizationMCP environment.
Unfollowing an artist or user modifies social graph data by removing a follow relationship. While this has a side effect on the user's account, it is reversible (the user can re-follow at any time), placing it in the Write category rather than Destructive. The blast radius is medium since an AI agent could unfollow multiple artists or users without explicit user intent, requiring manual effort to restore.
From the tool's definition 'Unfollow artists or users' — removing a follow relationship is a reversible write action (the user can re-follow)
Documented attack patterns abuse exactly the kind of access unfollow_artists_or_users gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PersonalizationMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for unfollow_artists_or_users:
{
"version": "1",
"default": "deny",
"tools": {
"unfollow_artists_or_users": {
"limits": [
{
"counter": "unfollow_artists_or_users_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}unfollow_artists_or_users stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unfollow artists or users. It is categorised as a Write tool in the PersonalizationMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Personalization MCP server in PolicyLayer and add a rule for unfollow_artists_or_users: 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 PersonalizationMCP. Nothing to install.
unfollow_artists_or_users 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 unfollow_artists_or_users 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 unfollow_artists_or_users. 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.
unfollow_artists_or_users is provided by the Personalization MCP server (yangliangwei/personalizationmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 PersonalizationMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 PersonalizationMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.