get_historical_prices
AI agents call get_historical_prices to retrieve information from Crypto Stocks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server purpose strongly suggest this retrieves historical price data without side effects. No modification, deletion, execution, or financial transaction occurs—it only queries and returns historical information. Even though the description is empty, the semantic meaning of 'get_historical_prices' in an investment tracking context maps clearly to a Read operation.
From the tool's definition Tool name 'get_historical_prices' and server context (tracking crypto-related stocks for investment analysis) indicate data retrieval. Tool description is empty, limiting confidence slightly.
Attacks that exploit this kind of access
get_historical_prices. It is categorised as a Read tool in the Crypto Stocks MCP Server, which means it retrieves data without modifying state.
Register the Crypto Stocks MCP server in PolicyLayer and add a rule for get_historical_prices: 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 Crypto Stocks. Nothing to install.
get_historical_prices 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_prices 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_prices. 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_prices is provided by the Crypto Stocks MCP server (kukapay/crypto-stocks-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 →