AI agents call get_votes to retrieve information from Topgg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical vote data from Top.gg for the current project. It performs a read-only operation that returns information without creating, modifying, deleting, or executing any external operations. The blast radius of misuse is minimal—an agent could only access vote history data that is likely already semi-public for a listed project.
From the tool's definition Tool name 'get_votes' and description 'Fetch a page of vote history' indicates retrieval of historical voting data with no modification or side effects.
Attacks that exploit this kind of access
Fetch a page of vote history for the current Top.gg project. It is categorised as a Read tool in the Topgg MCP Server, which means it retrieves data without modifying state.
Register the Topgg MCP server in PolicyLayer and add a rule for get_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 Topgg. Nothing to install.
get_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 get_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 get_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.
get_votes is provided by the Topgg MCP server (paillat-dev/topgg-mcp). 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 →