AI agents call crypto.token-price to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries price data from CoinGecko and returns informational metrics. It has no side effects, does not execute trades or move funds, and cannot modify any state. The MCP server settlement model (pay-per-call in USDC) is a billing mechanism for the tool's invocation, not a capability of the tool itself. Classification as Read is appropriate for a data lookup utility.
From the tool's definition Tool retrieves 'current spot price, market cap, 24h volume and 24h change for crypto assets' — purely data retrieval with no modification, execution, or financial transaction capability.
Attacks that exploit this kind of access
Current spot price, market cap, 24h volume and 24h change for crypto assets by CoinGecko asset id (lowercase, e.g. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for crypto.token-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 Mcp. Nothing to install.
crypto.token-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 crypto.token-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 crypto.token-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.
crypto.token-price is provided by the MCP server (@2sio/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 →