AI agents call search_provider 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.
The tool performs a query/search operation against lyrics providers and returns preview results only. No data is created, modified, deleted, or executed. The restriction to preview-only results and exclusion of full lyrics or raw payloads further confirms this is a benign read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Search a single provider' and 'preview-only potential matches' with 'MCP search results never include full lyrics or raw provider payloads.' This is a read-only search operation with no modification or execution…
Attacks that exploit this kind of access
Search a single provider (e.g., LRCLIB, Genius, Melon) for preview-only potential matches. MCP search results never include full lyrics or raw provider payloads. 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 search_provider: 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.
search_provider 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_provider 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_provider. 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_provider 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 →