AI agents use follow_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.
Following a playlist is a reversible write action that modifies the user's library/subscription state. It does not delete data or move money, and can be undone by unfollowing. The blast radius is moderate as it modifies user account state on an external platform.
From the tool's definition "Follow a playlist" - this creates a follow relationship between the user and a playlist on a platform (likely Spotify based on sibling tools)
Documented attack patterns abuse exactly the kind of access follow_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 follow_playlist:
{
"version": "1",
"default": "deny",
"tools": {
"follow_playlist": {
"limits": [
{
"counter": "follow_playlist_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}follow_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.
Follow 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 follow_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.
follow_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 follow_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 follow_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.
follow_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.