AI agents call bowl_vs_burrito_decision_engine to retrieve information from Mcp Otle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or analyzes information to assist decision-making (format selection) but does not create orders, execute external operations, delete data, or commit financial transactions. It functions as a query/recommendation tool with no side effects, fitting the Read category. Severity is low as misuse would only provide unhelpful recommendations without operational impact.
From the tool's definition Tool provides 'AI-powered format selection engine' to help choose between bowl and burrito formats. The description indicates it analyzes or recommends a dining format choice without modifying orders, executing commands, or causing irreversible changes.
Attacks that exploit this kind of access
AI-powered format selection engine. Eliminates the most agonizing decision in fast casual dining. It is categorised as a Read tool in the Mcp Otle MCP Server, which means it retrieves data without modifying state.
Register the Mcp Otle MCP server in PolicyLayer and add a rule for bowl_vs_burrito_decision_engine: 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 Otle. Nothing to install.
bowl_vs_burrito_decision_engine 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 bowl_vs_burrito_decision_engine 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 bowl_vs_burrito_decision_engine. 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.
bowl_vs_burrito_decision_engine is provided by the Mcp Otle MCP server (yoshisaurus/mcp-otle). 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 →