AI agents call song_history to retrieve information from Mcp Phish without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve historical data about songs, consistent with the read-only nature of the mcp-phish server which aggregates phish.net and phish.in APIs for music metadata and setlist information. The empty description lowers confidence slightly, but the server's purpose and naming pattern of sibling tools strongly indicate data retrieval with no side effects.
From the tool's definition Tool name 'song_history' and sibling tools (get_audio, get_reviews, get_show, get_song, get_track, search_shows, search_audio_tracks) indicate this is a Phish music API server providing music data retrieval only.
Attacks that exploit this kind of access
song_history. It is categorised as a Read tool in the Mcp Phish MCP Server, which means it retrieves data without modifying state.
Register the Mcp Phish MCP server in PolicyLayer and add a rule for song_history: 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 Mcp Phish. Nothing to install.
song_history 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 song_history 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 song_history. 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.
song_history is provided by the Mcp Phish MCP server (pete-builds/mcp-phish). 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 →