screen_universe
AI agents call screen_universe to retrieve information from Sablier MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without explicit description, confidence is reduced. However, 'screen' in finance universally means 'filter/query', and the tool name contains no action words suggesting modification (create, update, delete) or code execution. It fits the Read category as a portfolio analysis helper that retrieves or filters securities data.
From the tool's definition Tool name 'screen_universe' suggests filtering or querying a dataset of securities/assets (a 'universe' in financial terminology).
Attacks that exploit this kind of access
screen_universe. It is categorised as a Read tool in the Sablier MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sablier MCP Server MCP server in PolicyLayer and add a rule for screen_universe: 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 Sablier MCP Server. Nothing to install.
screen_universe 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 screen_universe 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 screen_universe. 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.
screen_universe is provided by the Sablier MCP Server MCP server (sablier-ai/sablier-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 →