AI agents use unfollow_playlist 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 a playlist removes the user's follow relationship with that playlist. While this could be considered reversible (the user can re-follow the playlist), it is a write/modification action on the user's social graph. It does not delete the playlist itself, so it is not Destructive. The action is reversible, placing it in the Write category.
From the tool's definition 'Unfollow a playlist' - unfollowing removes a subscription/follow relationship
Documented attack patterns abuse exactly the kind of access unfollow_playlist 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_playlist:
{
"version": "1",
"default": "deny",
"tools": {
"unfollow_playlist": {
"limits": [
{
"counter": "unfollow_playlist_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}unfollow_playlist 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 a playlist. 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_playlist: 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_playlist 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_playlist 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_playlist. 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_playlist 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.