get_all_open_positions
AI agents call get_all_open_positions to retrieve information from Mt5 Remote Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account position data from MetaTrader 5 without modifying, deleting, or executing any trades. It is a read-only query operation with no side effects. The server architecture confirms read-only semantics. Severity is low because position data is informational and poses minimal risk if accessed by an AI agent.
From the tool's definition Server is explicitly described as providing 'read-only access to positions, history, and logs without executing trades'. Tool name 'get_all_open_positions' retrieves position data. Description is empty but context is clear.
Attacks that exploit this kind of access
get_all_open_positions. It is categorised as a Read tool in the Mt5 Remote Reader MCP Server, which means it retrieves data without modifying state.
Register the Mt5 Remote Reader MCP server in PolicyLayer and add a rule for get_all_open_positions: 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 Remote Reader. Nothing to install.
get_all_open_positions 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 get_all_open_positions 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 get_all_open_positions. 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.
get_all_open_positions is provided by the Mt5 Remote Reader MCP server (marco7734/mt5-remote-reader-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 →