Request a CSV export of the account
AI agents call request_export_csv to retrieve information from Trading 212 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Requesting a CSV export retrieves account data in a downloadable format. While it 'requests' an export (which may trigger a background job), it does not modify, delete, or move money. The primary effect is reading/exporting data. Severity is low as the worst case is exposing account data in CSV form, but since this is the user's own account data, blast radius is limited.
From the tool's definition 'Request a CSV export of the account' - this initiates a data export/retrieval operation of account data
Attacks that exploit this kind of access
Request a CSV export of the account. It is categorised as a Read tool in the Trading 212 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trading 212 MCP Server MCP server in PolicyLayer and add a rule for request_export_csv: 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 Trading 212 MCP Server. Nothing to install.
request_export_csv 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 request_export_csv 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 request_export_csv. 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.
request_export_csv is provided by the Trading 212 MCP Server MCP server (razeevascx/212mcp). 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 →