AI agents call get_price to retrieve information from Coin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool belongs in the Read category because it retrieves market data (price information) with no side effects. Even though the description is empty, the semantic meaning of 'get_price' combined with the server's stated purpose ('market-data MCP server' enabling LLMs to 'answer market questions') and the pattern of sibling tools that are clearly data-retrieval functions strongly indicate this is a simple data fetch…
From the tool's definition Tool named 'get_price' with no description provided. Based on naming convention and context as part of a cryptocurrency market-data MCP server alongside tools like 'get_coin_details', 'get_coin_tickers', 'compare_prices', and 'get_aggregated_ohlc', this tool…
Attacks that exploit this kind of access
get_price. It is categorised as a Read tool in the Coin MCP Server, which means it retrieves data without modifying state.
Register the Coin MCP server in PolicyLayer and add a rule for get_price: 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 Coin. Nothing to install.
get_price 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_price 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_price. 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_price is provided by the Coin MCP server (sweetcornna/coin-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 →