list_problems
AI agents call list_problems to retrieve information from Online Judge MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query to list problems. It has no side effects, does not execute code, does not modify data, and does not involve financial transactions. The name and context of similar tools on the server strongly indicate a simple list/fetch operation. Empty description slightly reduces confidence but the name is clear enough.
From the tool's definition Tool name 'list_problems' indicates a retrieval operation that queries and returns a list of available problems from the Orange Juice Online Judge API.
Attacks that exploit this kind of access
list_problems. It is categorised as a Read tool in the Online Judge MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Online Judge MCP Server MCP server in PolicyLayer and add a rule for list_problems: 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 Online Judge MCP Server. Nothing to install.
list_problems 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 list_problems 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 list_problems. 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.
list_problems is provided by the Online Judge MCP Server MCP server (wangicheng/oj-mcp-server). 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 →