On-chain token metrics by contract address (via GeckoTerminal, free/keyless): name, symbol, decimals, on-chain USD price, FDV, market cap, total reserve in USD, 24h volume, total + normalized supply, image, and CoinGecko id. Distinct from crypto.token-price (CoinGecko aggregate spot) — this is DE...
AI agents call crypto.token-info 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 performs data retrieval only—it queries and returns token information without side effects or ability to modify state, execute code, or perform financial transactions. While the broader server handles financial settlement (x402/USDC), this specific tool is a passive query interface for public blockchain data.
From the tool's definition Tool retrieves read-only token metrics: 'name, symbol, decimals, on-chain USD price, FDV, market cap, total reserve in USD, 24h volume, total + normalized supply, image, and CoinGecko id.' The description explicitly states this queries on-chain data 'via…
Attacks that exploit this kind of access
On-chain token metrics by contract address (via GeckoTerminal, free/keyless): name, symbol, decimals, on-chain USD price, FDV, market cap, total reserve in USD, 24h volume, total + normalized supply, image, and CoinGecko id. Distinct from crypto.token-price (CoinGecko aggregate spot) — this is DEX-derived on-chain data for any token across 100+ networks. 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-info: 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-info 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-info 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-info. 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-info 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 →