AI agents call get_historical_data to retrieve information from Borsa MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns historical price data (Open, High, Low, Close, Volume) for financial instruments. It has no side effects, does not modify any data, and does not execute operations. The 'get_' prefix combined with the retrieval-only description confirms it as a Read category tool. Severity is low because misuse would only expose historical market data that is typically public information.
From the tool's definition Tool name 'get_historical_data' and description explicitly retrieves 'OHLCV price history with date range or period'. No modification, deletion, or execution capability—purely data retrieval.
Attacks that exploit this kind of access
Get OHLCV price history with date range or period (1d-5y). Supports BIST, US, and crypto. It is categorised as a Read tool in the Borsa MCP MCP Server, which means it retrieves data without modifying state.
Register the Borsa MCP server in PolicyLayer and add a rule for get_historical_data: 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 Borsa MCP. Nothing to install.
get_historical_data 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_historical_data 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_historical_data. 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_historical_data is provided by the Borsa MCP server (saidsurucu/borsa-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 →