BinSight

io.github.Alessiolucini由 GitHub 账号 Alessiolucini 发布v6.6.0更新于 Oct 26, 2026

The AI X-ray for any file: what is it, what does it hide, what changed. Built on REA.

已验证STDIO仅桌面开发者工具安全与监控

概览

AI 生成的概览

BinSight 在本机静态分析二进制文件及任意文件,让助手在不运行文件的情况下识别、检查并对比它们。

可以做什么
  • 初步分析与检查可执行文件:类型、架构、入口点、节区、导入导出、哈希、加固与代码签名,支持 ELF、PE 和 Mach-O。
  • 发现文件隐藏内容:工具链与加壳指纹、熵值、由导入推断的能力、加密常量、IOC 字符串与内嵌文件。
  • 对比文件:对任意两个文件做字节级差异,并对可执行文件给出导入、导出、节区与加固差异。
  • 搜索与指纹:字节、十六进制通配、文本与正则扫描,相似度哈希,Go 符号恢复与 SBOM 生成。
  • 生成报告:可分享的 Markdown 分析报告,并区分观察、推断与未知项。
适用场景
适合在需要弄清陌生下载文件、驱动、固件转储或应用更新时使用,也可用于判断二进制是否加壳或已签名,或查看两个版本之间改了什么,全程离线且不运行文件。
运行要求
通过 npx 以本地 stdio 进程运行(需要 Node.js)。仅限桌面端;未声明认证、环境变量或请求头。可在 macOS、Windows 和 Linux 上离线使用。
安装前请注意
它会读取你指定的文件,并把分析结果交给助手,因此不要指向你不愿与模型共享的敏感文件。它只做检测:不解包、不解密、不执行,结论属于证据与推断而非判定。

安装

在 SourceWeft 中

  1. 打开 控制台中的 BinSight,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

BinSight

The AI X-ray for any file. Point it at a binary and ask: what is it, what does it hide, and what changed?

Offline · cross-platform · with evidence. It never runs the file.

[MCP tool catalog] [license MIT]

Built on REA (morluto/rea) · MIT


Most files are black boxes: an .exe you downloaded, a firmware dump, a driver, a game, an ECU calibration, an app update. BinSight opens the box — statically, on your own machine, without ever running the file — and answers the three questions that matter, in plain language and with the evidence to back them up.

text
You: What is this file? Is it hiding anything? And what changed vs the old version?
BinSight: PE/Windows x64, compiled with MSVC, UPX-packed (entropy 7.9),          imports consistent with network + process injection, Authenticode          signature present, and vs the previous build 3 regions changed —          here are the offsets. All static, all offline, with evidence.

The three questions

🔎 What is it?

triage_file and inspect_executable read ELF, PE/Windows and Mach-O (and raw blobs) and tell you the type, architecture, entry point, imports/exports, sections, hashes, and a compiler/packer fingerprint — without starting Ghidra or IDA, on macOS, Windows or Linux.

🕵️ What does it hide?

detect_binary_toolchain, measure_binary_entropy, classify_import_capabilities, identify_crypto_constants, extract_binary_strings, inspect_code_signature and scan_embedded_content surface packing, high-entropy regions, imported capabilities (network, process, crypto…), IOC strings, embedded files, and whether a signature is real — reported as evidence and inference, never as a verdict.

🔁 What changed?

compare_binaries diffs any two files byte-for-byte and explains the change — which regions moved, what was zeroed or maxed out, the before/after values. Works on app updates, drivers, firmware and ECU calibration dumps alike. compare_executables adds import/export/section/hardening deltas for executables.

All 17 tools

ToolWhat it answers
triage_fileOne call: type, hashes, structure, entropy, packing, capabilities, signature, strings, next steps
generate_triage_reportA shareable Markdown triage report
compare_binariesDiff any two files and explain what changed (firmware, ECU dumps, updates)
compare_executablesDiff two executables: imports, exports, sections, hardening, entropy
inspect_executableSections, imports, exports, libraries, symbols, entry point, overlay — ELF/PE/Mach-O
inspect_binary_hardeningchecksec for every OS: PIE, canary, NX, RELRO, CFG, ASLR, hardened runtime
measure_binary_entropyFile / section / block Shannon entropy + chi-square
detect_binary_toolchainCompiler, packer, installer, language (UPX, MSVC, PyInstaller, Go…)
extract_binary_stringsASCII/UTF-16 strings classified into IOCs (URL, IP, path, registry…)
identify_crypto_constantsAES S-box, SHA/MD5, CRC32, ChaCha, curve parameters…
classify_import_capabilitiesCapabilities inferred from imports ("consistent with", never a verdict)
scan_byte_patternsByte / hex-wildcard / text / regex search, no provider needed
compute_similarity_hashesimphash, Rich hash, symhash, telfhash, ssdeep, TLSH
inspect_code_signatureAuthenticode + Mach-O code signature — on any host
scan_embedded_contentbinwalk-style embedded-file identification (offsets only)
generate_sbomCycloneDX / SPDX component inventory from embedded metadata
recover_go_symbolsFunction names from a stripped Go pclntab

Every result separates observations, inferences and unknowns, carries file offsets, and states its limitations. Detection only — nothing is unpacked, decrypted, cracked or executed.

Quickstart

bash
npx binsight triage-file /path/to/file --jsonnpx binsight compare-binaries /path/to/old /path/to/new --jsonnpx binsight generate-triage-report /path/to/file --json

Register BinSight as an MCP server for your AI agent, then just ask it in plain language ("what is this file, what does it hide, what changed?"):

bash
npx binsight setup

BinSight supports the same agents as REA — see supported agents; other clients can use manual MCP registration.

Verified against the reference tools

BinSight's parsers and hashes are checked against the tools analysts already trust: imphash matches pefile byte-for-byte, structure matches LIEF / readelf / otool, and hardening and packing results match checksec and Detect It Easy on a real corpus of ELF, PE and Mach-O binaries.

Documentation

Built on REA

BinSight builds on REA and adds the static intelligence suite above. REA is MIT-licensed; this project keeps that license and attribution. This is not an official REA release — for REA itself, go to morluto/rea.

License

MIT. See LICENSE. Portions © the REA authors.

来源:README.md,提交 70eeea2

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

2
  1. v6.6.0最新Oct 18, 2026
  2. v6.5.1Oct 17, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分