AI agents call get_recent_trades 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 retrieves cryptocurrency trade history without modifying data or executing transactions. It fits the Read category (retrieves/queries data with no side effects). The lack of a tool description introduces minor uncertainty, but the naming convention and server context strongly suggest this is a passive data retrieval operation typical of market-data APIs.
From the tool's definition Tool name 'get_recent_trades' indicates retrieval of historical trade data. Server context describes a 'market-data MCP server' focused on answering 'market questions.' Sibling tools (get_aggregated_ohlc, get_coin_details, get_coin_tickers, compare_prices)…
Attacks that exploit this kind of access
get_recent_trades. 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_recent_trades: 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_recent_trades 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_recent_trades 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_recent_trades. 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_recent_trades 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 →