AI agents call custom_screener to retrieve information from Finviz MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool description is empty, which lowers confidence slightly. However, based on the server's stated purpose ('stock screening and fundamental analysis') and the consistent pattern of sibling tools that perform screening operations (filtering/querying financial data without modification), custom_screener almost certainly retrieves or filters stock/market data.
From the tool's definition Tool name 'custom_screener' and server context showing 'stock screening and fundamental analysis capabilities'; sibling tools like 'dividend_growth_screener', 'earnings_screener', and 'etf_screener' are all read-only data retrieval operations from Finviz…
Documented attack patterns abuse exactly the kind of access custom_screener gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Finviz MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for custom_screener:
{
"version": "1",
"default": "deny",
"tools": {
"custom_screener": {}
}
}custom_screener is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
custom_screener. It is categorised as a Read tool in the Finviz MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Finviz MCP Server MCP server in PolicyLayer and add a rule for custom_screener: 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 Finviz MCP Server. Nothing to install.
custom_screener 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 custom_screener 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 custom_screener. 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.
custom_screener is provided by the Finviz MCP Server MCP server (tradermonty/finviz-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 35 Finviz MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
35 Finviz MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.