MANDATORY: Classifies the complexity of a dev task. If the user input is not in English, translate the core intent to English before calling (e.g.,
AI agents call classify_task to retrieve information from Oracle Models without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes information about task complexity to provide recommendations. It does not create, modify, delete, or execute any code or external operations. It is a pure analysis/classification function that returns recommendations, making it a Read category tool with low severity since misuse would only result in incorrect recommendations without side effects.
From the tool's definition The tool 'classify_task' performs classification and analysis of input data (development task complexity) without modifying, deleting, or executing any external operations.
Attacks that exploit this kind of access
MANDATORY: Classifies the complexity of a dev task. If the user input is not in English, translate the core intent to English before calling (e.g.,. It is categorised as a Read tool in the Oracle Models MCP Server, which means it retrieves data without modifying state.
Register the Oracle Models MCP server in PolicyLayer and add a rule for classify_task: 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 Oracle Models. Nothing to install.
classify_task 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 classify_task 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 classify_task. 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.
classify_task is provided by the Oracle Models MCP server (vanppsa/oracle-models). 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 →