Получить историю операций по счёту в Т-Инвестициях
AI agents call get_operations to retrieve information from T-Invest MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that retrieves past account operations and transaction history. It has no side effects, does not modify data, execute commands, or involve financial transactions. While the server includes sensitive financial data access, this specific tool only fetches historical records without the ability to alter account state or initiate transfers/trades.
From the tool's definition Tool name 'get_operations' and description 'Get history of operations on account in T-Invest' indicate retrieval of historical transaction/operation data with no modification capability.
Attacks that exploit this kind of access
Получить историю операций по счёту в Т-Инвестициях. It is categorised as a Read tool in the T-Invest MCP Server MCP Server, which means it retrieves data without modifying state.
Register the T-Invest MCP Server MCP server in PolicyLayer and add a rule for get_operations: 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 T-Invest MCP Server. Nothing to install.
get_operations 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_operations 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_operations. 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_operations is provided by the T-Invest MCP Server MCP server (nonnname/t-invest-mcp-server). 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 →