AI agents call vicsee_get_task to retrieve information from Vicsee without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries the status of an existing task. It has no side effects, does not modify data, and does not trigger any external operations. The term 'poll' in API contexts universally refers to checking status without state changes. Severity is low because even if misused, it only retrieves status metadata with no blast radius.
From the tool's definition Tool description states "Poll a generation or upscale task by its id" with no mention of modifying, deleting, or executing operations. Polling retrieves task status information only.
Attacks that exploit this kind of access
Poll a generation or upscale task by its id. status is one of. It is categorised as a Read tool in the Vicsee MCP Server, which means it retrieves data without modifying state.
Register the Vicsee MCP server in PolicyLayer and add a rule for vicsee_get_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 Vicsee. Nothing to install.
vicsee_get_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 vicsee_get_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 vicsee_get_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.
vicsee_get_task is provided by the Vicsee MCP server (vicseeai/vicsee-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 →