Live on-chain token metadata for an ERC-20 or ERC-721 contract (Base, Ethereum, Polygon, Arbitrum, Optimism; keyless). Returns name, symbol, decimals, detected standard, and total supply (raw + formatted). The authoritative read straight from the contract — complements crypto.token-price and cryp...
AI agents call crypto.token-metadata 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 retrieves immutable on-chain metadata from token contracts without modifying state, executing code conditionally, or affecting financial transactions. It is a straightforward read operation. While the MCP server is financially-oriented (pay-per-call in USDC), this specific tool only queries and returns data, posing minimal security risk even if called by an AI agent.
From the tool's definition Tool description states it 'Returns name, symbol, decimals, detected standard, and total supply' and describes itself as 'The authoritative read straight from the contract' — purely informational queries with no side effects.
Attacks that exploit this kind of access
Live on-chain token metadata for an ERC-20 or ERC-721 contract (Base, Ethereum, Polygon, Arbitrum, Optimism; keyless). Returns name, symbol, decimals, detected standard, and total supply (raw + formatted). The authoritative read straight from the contract — complements crypto.token-price and crypto.contract (ABI/source. 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-metadata: 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-metadata 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-metadata 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-metadata. 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-metadata 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 →