Get event votes for a year.
AI agents call ctftime_votes to retrieve information from Mcp Ctftime without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves voting data from the CTFtime API without side effects. It performs a simple data query operation characteristic of Read category tools. No data is created, modified, deleted, or executed—it merely fetches existing vote information for a specified year.
From the tool's definition Tool name 'ctftime_votes' combined with description 'Get event votes for a year' indicates a retrieval operation. The server description confirms this is querying 'public CTFtime API' data including 'votes', with no mention of modification capabilities.
Attacks that exploit this kind of access
Get event votes for a year. It is categorised as a Read tool in the Mcp Ctftime MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ctftime MCP server in PolicyLayer and add a rule for ctftime_votes: 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 Mcp Ctftime. Nothing to install.
ctftime_votes 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 ctftime_votes 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 ctftime_votes. 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.
ctftime_votes is provided by the Mcp Ctftime MCP server (tomek7667/mcp-ctftime). 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 →