What is Code Reason?
Code Reason is an MCP server that gives coding agents real program-analysis capabilities — data-flow reachability, call-graph traversal, evidence-chain construction, and source/sink taint analysis. It is built on Fraunhofer AISEC's Code Property Graph for Java and Python codebases and is designed for any MCP-compatible coding agent.
How to use Code Reason?
Add code-reason as an MCP server to your coding agent (tested with Claude Code). First call reason_analyze_project to build the CPG, then use any of the other 9 tools — such as reason_find_entry_points, reason_query_dataflow, or reason_trace_taint_path — for unlimited in-memory queries against the same analysis.
Key features of Code Reason
- Provides 9 MCP tools for program analysis
- Built on Fraunhofer AISEC’s Code Property Graph for Java and Python
- One analyze pass, unlimited subsequent queries
- Compact JSON evidence chains with intermediate steps and code context
- ~30–40% fewer agent tokens on multi-step security reviews
- Works with any MCP-compatible coding agent
Use cases of Code Reason
- Multi-step security reviews of Java or Python codebases
- Detecting SQLi, XSS, and command injection via catalog-driven scanning
- Tracing taint paths from input sources to sensitive sinks
- Understanding call-graph relationships and data flow across functions
- Replacing manual grep-based speculation with ground-truth analysis
Comments