Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Firzus/reverse-engineer

NPM · REVERSE-ENGINEER

Read-only reverse engineering of Electron apps, PE/ELF/Mach-O binaries, Go/Rust, .NET and APKs.

Available components

+3 this week 86 Trust /100

Last scanned (3 hours ago)

Scores higher than 90% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to Firzus/agent-skills). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 12 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 846 tokens (~105/item across 8 items; 8 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
  • Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage86
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 58% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 30 Oct 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 29 Oct 26 +1
    • Security disclosure: fail → unverified ▼ functional
  • 27 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 +16
    • Malware scan: unverified → pass ▲ security
  • 23 Oct 26 −3
    • Malware scan: pass → unverified ▼ security
    • Provenance: fail → pass ▲ security
    • The attested source repository moved: Firzus/agent-skills security
    • Stability: unverified → 0.13 ▲ functional
    • Package version: 0.1.0-alpha.1 → 0.1.0-alpha.2 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed npm/reverse-engineer@0.1.0-alpha.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo Firzus/agent-skills
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Firzus/agent-skills/.github/workflows/reverse-engineer-publish.yml@refs/heads/main
Rekor log index 3420382003
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:e6144eaa453f0848b13622107aff99945126bae4e050a9882913e5f8ef86ed6be76a98b470599c992ef99f3513e27fdf8c1b3578831c0a77ebf40c9c6

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 8 exposed · ~788 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
binary_inventory ~98

PE, ELF or Mach-O inventory. part=summary (default): format, sections, libraries with imports, exports, Node addon names, notable strings. Other parts list one table, paged with skip and filtered by a regex.

NameTypeReqDescription
filterstring–Case-insensitive regex on names or strings
maxinteger––
partstring––
pathstringyes–
skipinteger––

No output schema declared.

No examples provided.

buildinfo ~63

Go build info (toolchain, main package, module, build settings, dependency versions) and Rust cargo-auditable dependencies, parsed from the binary without running it.

NameTypeReqDescription
filterstring–Regex on dependency paths or crate names
pathstringyes–

No output schema declared.

No examples provided.

decompile ~103

Ghidra headless decompilation, cached per file. First call analyzes the binary (can take minutes). function=NAME|ADDRESS returns its C; containing=TEXT lists functions that reference a string; neither lists functions.

NameTypeReqDescription
containingstring–Find functions that reference this string
functionstring–Function name, FUN_xxx or address
maxinteger––
pathstringyes–
skipinteger––

No output schema declared.

No examples provided.

electron_surface ~112

Electron app map: extracts app.asar (cached), main entry, preloads and exposed APIs, native .node addons and the addon names called from JS, IPC channels grouped by call site, fuses, asar integrity. Use focus (one or more words) to filter on one feature.

NameTypeReqDescription
focusstring–Feature words, comma-separated, e.g. audio,microphone; filters channels and lists matching identifiers
pathstringyesApp directory, resources directory, executable or .asar

No output schema declared.

No examples provided.

managed ~74

.NET assemblies (via ilspycmd) and APK/DEX/JAR (via jadx): decompile once into the cache, summarize namespaces, manifest, P/Invoke and native libraries; type=Name returns one type's source.

NameTypeReqDescription
pathstringyes–
typestring–Fully qualified or short type name

No output schema declared.

No examples provided.

read ~128

Read a slice: lines start..end; for minified code a column window (start=line, col, length); for binaries a hexdump at offset. A directory path lists its entries.

NameTypeReqDescription
colinteger–Column in line `start` for minified code
endinteger–Last line, default start+79
lengthinteger–Characters (col/offset mode) or bytes
offsetinteger–Byte offset (hexdump for binaries)
pathstringyes–
startinteger–First line (1-based)

No output schema declared.

No examples provided.

search ~154

Search a directory, an extracted app, a .asar (auto-extracted) or one file. Hidden folders included, node_modules skipped by default. Returns file:line:col (or file@offset for binaries) with a short excerpt.

NameTypeReqDescription
contextinteger–Characters of context on each side
globstring–Filter, e.g. *.js or .webpack/**/*.js
ignore_caseboolean––
include_depsboolean–Also search node_modules
maxinteger––
pathstringyesDirectory, .asar or file
patternstringyesLiteral text, or a JavaScript regex when regex=true
regexboolean––

No output schema declared.

No examples provided.

triage ~56

Identify a file or directory: format, architecture, size, SHA-256, markers (Go, Rust, Electron, N-API, packers) and the next tool to call.

NameTypeReqDescription
pathstringyesFile or directory

No output schema declared.

No examples provided.

Install

How do I install the io.github.Firzus/reverse-engineer MCP server?

io.github.Firzus/reverse-engineer runs locally as an npm package, launched with npx -y reverse-engineer. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · reverse-engineer

# add to Claude Code
claude mcp add firzus-reverse-engineer -- npx -y reverse-engineer
Common questions

What is the io.github.Firzus/reverse-engineer MCP server?

io.github.Firzus/reverse-engineer is an MCP server listed in the public MCP registry as io.github.Firzus/reverse-engineer. Read-only reverse engineering of Electron apps, PE/ELF/Mach-O binaries, Go/Rust, .NET and APKs. This page covers its npm package (reverse-engineer).

Is the io.github.Firzus/reverse-engineer MCP server safe to use?

io.github.Firzus/reverse-engineer scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.Firzus/reverse-engineer MCP server expose?

io.github.Firzus/reverse-engineer exposes 8 tools: triage, electron_surface, search, read, binary_inventory, and 3 more. Their descriptions and schemas cost roughly 788 tokens of context every time the server is loaded.

Is the io.github.Firzus/reverse-engineer MCP server still maintained?

io.github.Firzus/reverse-engineer is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.Firzus/reverse-engineer MCP server under?

io.github.Firzus/reverse-engineer declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.