将歌曲添加到播放列表
AI agents use add_to_playlist to create or update resources in Claude Music MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Music MCP environment.
The tool creates or modifies playlist data by adding songs, fitting the Write category. It is not destructive (songs can be removed), not executable code, and has no financial impact. Severity is low because accidental additions are easily reversed and have minimal blast radius—playlists can be edited or recreated without consequence.
From the tool's definition Tool adds songs to playlists, which modifies playlist data. Description translates to 'Add songs to playlist'. This is a Create/Modify operation on playlist contents.
Attacks that exploit this kind of access
将歌曲添加到播放列表. It is categorised as a Write tool in the Claude Music MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Music MCP server in PolicyLayer and add a rule for add_to_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 Claude Music MCP. Nothing to install.
add_to_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 add_to_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 add_to_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.
add_to_playlist is provided by the Claude Music MCP server (leehave/claude-music-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 →