AI agents call models.compare to retrieve information from Or Info without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays comparative data about models (pricing, context, benchmarks, features) but does not create, modify, delete, execute code, or perform financial transactions. It is purely informational and read-only in nature.
From the tool's definition Tool description states 'Side-by-side comparison of two models: pricing, context, benchmarks and features' - performs retrieval and comparison of model information without modification.
Attacks that exploit this kind of access
Side-by-side comparison of two models: pricing, context, benchmarks and features. It is categorised as a Read tool in the Or Info MCP Server, which means it retrieves data without modifying state.
Register the Or Info MCP server in PolicyLayer and add a rule for models.compare: 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 Or Info. Nothing to install.
models.compare 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 models.compare 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 models.compare. 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.
models.compare is provided by the Or Info MCP server (jmtrs/or-info). 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 →