AI agents call get_reviews 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 retrieves or queries review data with no apparent side effects. It follows the naming and functional pattern of other Read tools in the same server. Even without an explicit description, the 'get_' prefix and context of a read-only music API (phish.net/phish.in) indicate this is a simple data fetch operation with no mutation, execution, or destructive capability.
From the tool's definition Tool name 'get_reviews' combined with server purpose (Phish music API integration for setlists, songs, jam-charts, reviews, and audio) indicates data retrieval.
Attacks that exploit this kind of access
get_reviews. 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 get_reviews: 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.
get_reviews 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 get_reviews 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 get_reviews. 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.
get_reviews 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 →