Generates a random dish adjective.
AI agents call food-adjective to retrieve information from Faker MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only generates fake/random data locally using Faker.js with no side effects, no data persistence, and no external interactions. It simply returns a string adjective describing a dish.
From the tool's definition Generates a random dish adjective
Attacks that exploit this kind of access
Generates a random dish adjective. It is categorised as a Read tool in the Faker MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Faker MCP Server MCP server in PolicyLayer and add a rule for food-adjective: 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 Faker MCP Server. Nothing to install.
food-adjective 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 food-adjective 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 food-adjective. 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.
food-adjective is provided by the Faker MCP Server MCP server (kentrino/faker-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 →