AI agents call models.top 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 ranks existing model data based on task and budget parameters. It has no side effects—it does not create, modify, delete, or execute any operations. The most severe realistic misuse would be to waste compute time on queries, which is low-impact. No destructive, financial, or code-execution risk.
From the tool's definition Tool performs ranking/retrieval of model information ('Rank the best models') with no modification of data. Server description confirms this is for 'query' and 'comparisons' of model metadata.
Attacks that exploit this kind of access
Rank the best models for a specific task, optionally within a price budget. 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.top: 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.top 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.top 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.top. 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.top 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 →