Directional Movement Index (DX)
AI agents call technicalIndicators_dx to retrieve information from MCP Avantage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical financial data and computes a read-only technical indicator (DX). It has no side effects, does not execute trades or financial transactions, and does not modify any data. The blast radius of misuse is minimal—an AI agent could only receive misleading technical analysis output, which does not result in financial loss or irreversible actions without additional tools.
From the tool's definition Directional Movement Index (DX) is a technical indicator that retrieves and calculates directional movement data from financial time series.
Attacks that exploit this kind of access
Directional Movement Index (DX). It is categorised as a Read tool in the MCP Avantage MCP Server, which means it retrieves data without modifying state.
Register the MCP Avantage MCP server in PolicyLayer and add a rule for technicalIndicators_dx: 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 MCP Avantage. Nothing to install.
technicalIndicators_dx 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 technicalIndicators_dx 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 technicalIndicators_dx. 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.
technicalIndicators_dx is provided by the MCP Avantage MCP server (missionsquad/mcp-avantage). 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 →