Run a pre-built intelligent screen.
AI agents call smart_screen to retrieve information from Rozkoduj MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Running a pre-built screen is a read operation that queries and filters market data (stocks, crypto, forex) based on predefined criteria. No data is modified, no commands are executed, and no financial transactions are made. The sibling tools (analyze, fundamentals, market_pulse, movers) all suggest a read-oriented server. Severity is low as misuse would only expose market data.
From the tool's definition "Run a pre-built intelligent screen" — screening/filtering is a read/query operation that retrieves filtered market data
Attacks that exploit this kind of access
Run a pre-built intelligent screen. It is categorised as a Read tool in the Rozkoduj MCP MCP Server, which means it retrieves data without modifying state.
Register the Rozkoduj MCP server in PolicyLayer and add a rule for smart_screen: 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 Rozkoduj MCP. Nothing to install.
smart_screen 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 smart_screen 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 smart_screen. 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.
smart_screen is provided by the Rozkoduj MCP server (rozkoduj/rozkoduj-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 →