Decode an EVM smart contract. Pass chain (ethereum, base, polygon, arbitrum, optimism, bsc, avalanche) + address → whether source-verified (Sourcify), name/compiler/language, proxy + implementation, and human-readable function/event signatures from the ABI. Optional selector (0x 4-byte) → decode ...
AI agents call crypto.contract 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 purely informational queries about smart contract code and structure. It retrieves pre-existing verified source code, ABI data, and contract metadata without invoking any contract functions, modifying state, or executing operations. The optional selector decoding is similarly a read-only lookup in the ABI or 4byte directory. No financial transactions, code execution, or data modification occurs.
From the tool's definition Tool retrieves and decodes smart contract information: 'Decode an EVM smart contract', 'whether source-verified', 'name/compiler/language', 'function/event signatures from the ABI'. Returns read-only data with no state changes or execution of contract logic.
Attacks that exploit this kind of access
Decode an EVM smart contract. Pass chain (ethereum, base, polygon, arbitrum, optimism, bsc, avalanche) + address → whether source-verified (Sourcify), name/compiler/language, proxy + implementation, and human-readable function/event signatures from the ABI. Optional selector (0x 4-byte) → decode what it calls (from the contract ABI if verified, else the 4byte directory). Pairs with crypto.tx. Free, keyless. 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.contract: 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.contract 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.contract 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.contract. 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.contract 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 →