Get function signatures for the given selector from 4byte.directory
AI agents call 4byte to retrieve information from Blockchain MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only tool that queries the 4byte.directory service to decode function selectors into their human-readable signatures. It performs no writes, deletions, code execution, or financial operations. The blast radius is minimal—misuse could only retrieve information already publicly available. Classified as Read with low severity.
From the tool's definition The tool 'Get function signatures for the given selector from 4byte.directory' retrieves/queries data from an external directory without modifying any data or causing side effects. It is purely a lookup operation.
Attacks that exploit this kind of access
Get function signatures for the given selector from 4byte.directory. It is categorised as a Read tool in the Blockchain MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Blockchain MCP Server MCP server in PolicyLayer and add a rule for 4byte: 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 Blockchain MCP Server. Nothing to install.
4byte 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 4byte 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 4byte. 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.
4byte is provided by the Blockchain MCP Server MCP server (lienhage/blockchain-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 →