Switch to a different trading account
AI agents use ig_switch_account to create or update resources in IG Trading MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your IG Trading MCP environment.
Switching accounts is a reversible write operation that changes which account subsequent trading operations target. While not destructive or financial in itself, it modifies application state and has high severity because an AI agent switching to an unintended account could cause trades to execute on the wrong account, resulting in unintended financial exposure or losses.
From the tool's definition Tool name 'ig_switch_account' and description 'Switch to a different trading account' indicate modification of account state/context.
Attacks that exploit this kind of access
Switch to a different trading account. It is categorised as a Write tool in the IG Trading MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the IG Trading MCP server in PolicyLayer and add a rule for ig_switch_account: 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 IG Trading MCP. Nothing to install.
ig_switch_account 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 ig_switch_account 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 ig_switch_account. 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.
ig_switch_account is provided by the IG Trading MCP server (kea0811/ig-trading-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 →