Abre Documatic por nombre de clase (ej. %Library.String).
AI agents call open_class to retrieve information from IRIS ObjectScript MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool opens/retrieves documentation for a specified IRIS class. It is a read operation with no side effects, simply fetching and displaying class reference documentation. Misuse potential is minimal.
From the tool's definition 'Abre Documatic por nombre de clase' — opens documentation for a class by name, a read-only retrieval operation
Attacks that exploit this kind of access
Abre Documatic por nombre de clase (ej. %Library.String). It is categorised as a Read tool in the IRIS ObjectScript MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IRIS ObjectScript MCP Server MCP server in PolicyLayer and add a rule for open_class: 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 IRIS ObjectScript MCP Server. Nothing to install.
open_class 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 open_class 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 open_class. 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.
open_class is provided by the IRIS ObjectScript MCP Server MCP server (sorodriguezz/iris-mcp-intelligence). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
open_class is one line of IRIS ObjectScript MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →