Trace a transaction to discover every contract it touches internally. Uses debug_traceCall to extract the full call tree, then scans each unique contract for exploit patterns. Use this for deep inspection of multi-contract interactions (e.g., swaps routing through many pools).
AI agents call trace_transaction to retrieve information from Aegis Defi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
trace_transaction performs retrospective analysis of transaction behavior. It retrieves transaction call trees and scans contracts for patterns, which are read operations. While it inspects for exploit patterns (security-focused analysis), it does not execute transactions, modify state, move funds, or delete data.
From the tool's definition Tool 'traces a transaction to discover every contract it touches internally' and 'scans each unique contract for exploit patterns.' The description emphasizes inspection and analysis (debug_traceCall extraction, pattern scanning) with no mention of state…
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Trace a transaction to discover every contract it touches internally. Uses debug_traceCall to extract the full call tree, then scans each unique contract for exploit patterns. Use this for deep inspection of multi-contract interactions (e.g., swaps routing through many pools). It is categorised as a Read tool in the Aegis Defi MCP Server, which means it retrieves data without modifying state.
Register the Aegis Defi MCP server in PolicyLayer and add a rule for trace_transaction: 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 Aegis Defi. Nothing to install.
trace_transaction 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 trace_transaction 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 trace_transaction. 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.
trace_transaction is provided by the Aegis Defi MCP server (stanleythegoat/aegis). 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 →