CutterMCP-plus
Provides an MCP-enabled interface to Cutter (reverse engineering tool). It exposes Cutter operations (listing functions/globals/strings/segments, decompiling/disassembling, xrefs, renaming, comments/types, and reading bytes/addresses) via a local HTTP plugin inside Cutter and an MCP wrapper that can run in STDIO or streamable HTTP mode.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Runs primarily as local services (127.0.0.1) and communicates via HTTP/stdio. README does not describe TLS, authentication, authorization, or rate limiting. It explicitly warns about injection risks from strings during malware analysis and cautions against blindly executing commands; however, no concrete sandboxing or input sanitization details are provided.
⚡ Reliability
Best When
Used locally for interactive reverse engineering and analysis where an agent can call deterministic Cutter actions (decompile/disasm/xrefs) and the operator can review results.
Avoid When
Avoid exposing the server to untrusted networks, and avoid deploying in multi-tenant settings without strong network and auth controls.
Use Cases
- • Accelerate reverse engineering workflows with LLM-assisted reasoning over disassembly/decompilation
- • Assist CTF-style program analysis and challenge solving
- • Aid malware analysis by summarizing/renaming functions and extracting key information
Not For
- • Production, internet-facing deployments (runs as a local server; no documented auth)
- • Environments requiring strict compliance/SLA guarantees
- • Automated execution of potentially dangerous actions without human review
Interface
Authentication
No authentication mechanism is described for the local HTTP endpoints or MCP wrapper. Usage appears to assume a trusted local environment (127.0.0.1).
Pricing
The project itself appears open-source; costs depend on whichever external LLM(s) are used by the agent/host.
Agent Metadata
Known Gotchas
- ⚠ Local HTTP server endpoints are assumed trusted; avoid exposing beyond localhost
- ⚠ Token spending can be significant for LLM-driven steps
- ⚠ Analysis results may be influenced by anti-analysis/obfuscation; agent may need extra disassembly/direct inspection
- ⚠ Some operations change Cutter state (renames/comments/types), so agent should avoid unintended repeated modifications
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for CutterMCP-plus.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.