Update the stop loss and/or take profit on an open position.
AI agents use modify_position to create or update resources in MetaTrader 5 MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MetaTrader 5 MCP environment.
This tool modifies parameters on an existing open trading position (stop loss and take profit levels). While it doesn't directly move money or place/close trades, changing these levels on a live financial position can significantly affect trade outcomes and risk exposure.
From the tool's definition Update the stop loss and/or take profit on an open position
Attacks that exploit this kind of access
Update the stop loss and/or take profit on an open position. It is categorised as a Write tool in the MetaTrader 5 MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MetaTrader 5 MCP server in PolicyLayer and add a rule for modify_position: 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. Nothing to install.
modify_position is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the modify_position 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 modify_position. 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.
modify_position is provided by the MetaTrader 5 MCP server (rpieterse/mcp-studio-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 →