stock_kdj
AI agents call stock_kdj to retrieve information from FNewsCrawler without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on naming convention and server context, stock_kdj appears to be a read-only data retrieval tool for financial indicators. No evidence of side effects, code execution, data modification, or financial transactions. Sibling tools confirm the server's role is data aggregation and querying only. The empty description prevents higher confidence, but the pattern is clear.
From the tool's definition Tool name 'stock_kdj' suggests retrieval of KDJ indicator data (a technical analysis metric). Sibling tools on this server are all data retrieval functions (get_ak_*, get_eastmoney_*) with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
stock_kdj. It is categorised as a Read tool in the FNewsCrawler MCP Server, which means it retrieves data without modifying state.
Register the FNewsCrawler MCP server in PolicyLayer and add a rule for stock_kdj: 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 FNewsCrawler. Nothing to install.
stock_kdj 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 stock_kdj 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 stock_kdj. 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.
stock_kdj is provided by the FNewsCrawler MCP server (noimank/fnewscrawler). 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 →