背离检测，检测价格与指标之间的背离信号
AI agents call divergence_detector to retrieve information from Trade MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs technical analysis by detecting divergences between price movements and technical indicators (likely using TA-Lib as mentioned in server description). It analyzes and returns signals/insights from existing market data without executing orders, modifying positions, moving funds, or triggering external operations.
From the tool's definition Tool name 'divergence_detector' and description '背离检测，检测价格与指标之间的背离信号' (divergence detection, detecting divergence signals between price and indicators) indicates technical analysis computation on market data without executing trades or modifying state.
Attacks that exploit this kind of access
背离检测，检测价格与指标之间的背离信号. It is categorised as a Read tool in the Trade MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trade MCP Server MCP server in PolicyLayer and add a rule for divergence_detector: 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 Trade MCP Server. Nothing to install.
divergence_detector 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 divergence_detector 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 divergence_detector. 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.
divergence_detector is provided by the Trade MCP Server MCP server (woodsgao/trade-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 →