Data flow analysis endpoint (forward/backward variable tracking)
envgap__bethington__ghidra-mcp-111
01 / FAILURE SIGNATURE
As reported upstream
No identifying execution failure has been captured.
Not a benchmark task.
- In a clean container the reported failure did not reproduce, or the known fix did not make the project run.
02 / ENVIRONMENT RECIPE
- Base commit
0792d57aa05eedd1bdbb0a922682e9edb6d08cc1- Manifest
pom.xml- Reproduce
Awaiting issue-specific recipe- Run under trace
Awaiting a meaningful runtime command
03 / ORIGINAL ISSUE TEXT
bethington/ghidra-mcp #111 · read the original issue
## Summary Add a data flow analysis tool that traces how values propagate through a function — forward (where does this value go?) and backward (where did this value come from?). ## Motivation When a model tries to understand what a function does, knowing 'this parameter flows into a memcpy size argument' or 'this return value came from a network read' is extremely high-signal context. It's the kind of information that makes the difference between naming a function \ProcessData\ vs \ParseNetworkPacketHeader\. Currently no equivalent exists in our 193 tools. starsong-consulting/GhydraMCP has \nalysis_get_dataflow\ with forward/backward direction and max_steps. ## Design Ideas - New \@McpTool\ method in AnalysisService - Parameters: address, variable/register, direction (forward/backward), max_steps - Uses Ghidra's \DecompInterface\ Varnode/PcodeOp graph traversal - Returns chain of operations showing data producers/consumers - Self-contained: 200-300 lines of Java, no existing code changes ## Effort Estimate Medium-High — requires understanding Ghidra's Varnode graph API, but implementation is self-contained in AnalysisService. ## References - starsong-consulting/GhydraMCP \nalysis_get_dataflow\ - Ghidra \DecompInterface\ / \HighFunction\ / \Varnode\ APIs
04 / LABELS
Labels from the report text only; not yet run
No supported category has been assigned.
Label rules and the text that matched
[]