AI agents call format_lyrics to retrieve information from Mr Magic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries lyrics data sources and formats the output for display, performing a read-only operation. There is no indication of data creation, modification, deletion, or execution of external commands. The in-memory processing and return of formatted text is characteristic of a Read category tool. Severity is low as misuse would only affect data retrieval and display.
From the tool's definition Tool description states 'Find lyrics and return formatted text (with optional romanization) in-memory.' The verb 'return' and 'in-memory' indicate data retrieval with no side effects or persistence.
Attacks that exploit this kind of access
Find lyrics and return formatted text (with optional romanization) in-memory. It is categorised as a Read tool in the Mr Magic MCP Server, which means it retrieves data without modifying state.
Register the Mr Magic MCP server in PolicyLayer and add a rule for format_lyrics: 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 Mr Magic. Nothing to install.
format_lyrics 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 format_lyrics 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 format_lyrics. 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.
format_lyrics is provided by the Mr Magic MCP server (mr-magic-mcp-server). 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 →