Decode raw EVM transaction calldata. POST { data } (0x-prefixed hex). Resolves the 4-byte function selector to its human signature(s) via the openchain.xyz database, then ABI-decodes the parameters (address, uint/int, bool, bytesN, string, bytes, and elementary dynamic arrays). Returns selector, ...
AI agents call crypto.decode-calldata 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 decoding and analysis of blockchain transaction data without modifying state, executing transactions, or moving funds. It is purely informational—taking encoded calldata as input and returning human-readable function signatures and decoded parameters. No side effects, no irreversible changes, no code execution triggered. This is a Read operation typical of blockchain analysis and auditing tools.
From the tool's definition Decode raw EVM transaction calldata. POST { data } (0x-prefixed hex). Resolves the 4-byte function selector to its openchain.xyz database, then ABI-decodes the parameters...
Attacks that exploit this kind of access
Decode raw EVM transaction calldata. POST { data } (0x-prefixed hex). Resolves the 4-byte function selector to its human signature(s) via the openchain.xyz database, then ABI-decodes the parameters (address, uint/int, bool, bytesN, string, bytes, and elementary dynamic arrays). Returns selector, candidate signatures, d. 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.decode-calldata: 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.decode-calldata 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.decode-calldata 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.decode-calldata. 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.decode-calldata 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 →