MT5 ターミナルとの接続状態・バージョン情報を返す。
AI agents call mt5_health_check to retrieve information from MT5 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 a diagnostic check that retrieves connection status and version metadata from the MT5 terminal. It has no side effects—it only reads and reports existing state information. This is a typical health-check or status-query operation, placing it firmly in the Read category. The low severity reflects minimal blast radius even if misused by an agent.
From the tool's definition Tool name 'mt5_health_check' and description stating it 'returns connection status and version information with MT5 terminal' indicates data retrieval only.
Attacks that exploit this kind of access
MT5 ターミナルとの接続状態・バージョン情報を返す。. It is categorised as a Read tool in the MT5 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MT5 MCP Server MCP server in PolicyLayer and add a rule for mt5_health_check: 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 MT5 MCP Server. Nothing to install.
mt5_health_check 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 mt5_health_check 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 mt5_health_check. 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.
mt5_health_check is provided by the MT5 MCP Server MCP server (junmt/mt5-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 →