Get the total number of open positions.
AI agents call positions_total to retrieve information from MetaTrader 5 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account state information (count of open positions) with no side effects. It is a read-only query similar to list or get operations. While it provides information about active trading positions, the retrieval itself poses minimal risk—the danger lies in how an agent might act on this data, not in the tool's own operation.
From the tool's definition Tool name 'positions_total' and description 'Get the total number of open positions' indicate a query operation that retrieves data without modification or execution of trades.
Attacks that exploit this kind of access
Get the total number of open positions. It is categorised as a Read tool in the MetaTrader 5 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MetaTrader 5 MCP Server MCP server in PolicyLayer and add a rule for positions_total: 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 MetaTrader 5 MCP Server. Nothing to install.
positions_total 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 positions_total 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 positions_total. 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.
positions_total is provided by the MetaTrader 5 MCP Server MCP server (jorgearturoyap-debug/metatrader-5-for-chatgpt-desktop). 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 →