This record as markdown: /tools/4shil-ytm-mcp/search-song.md
What search_song does on Ytm
AI agents call search_song to retrieve information from Ytm without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why search_song is rated Low
Search operations are fundamentally retrieval-based with no side effects. The tool queries YouTube Music's database and returns results. Even in the context of a media control server with capabilities like downloading, playlist management, and playback control, a search function is purely informational. Low severity because misuse would only result in unwanted search queries with minimal blast radius.
From the tool's definition Tool description states 'Search YouTube Music for a song' - this is a query operation that retrieves data without modifying or executing actions. No side effects, no data modification, no command execution.
Attacks that exploit this kind of access
The rule that runs search_song safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ytm, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_song, this is the rule to start with:
search_song is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ytm, apply this rule, and every search_song call is checked against it from then on.
Questions about search_song
Search YouTube Music for a song. It is categorised as a Read tool in the Ytm MCP Server, which means it retrieves data without modifying state.
Register the Ytm MCP server in PolicyLayer and add a rule for search_song: 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 Ytm. Nothing to install.
search_song is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_song 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 search_song. 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.
search_song is provided by the Ytm MCP server (4shil/ytm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ytm, and thousands of servers like it.
This server
Across the catalogue