Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Independent deterministic verification for AI-written software. Local, evidence-backed checks.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。
在终端中运行这条命令
浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 b2ige2-a11y 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Qemu MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Boot and drive QEMU VMs from an AI agent: keys, screenshots, serial. No guest agent.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
B2IGE Verify is deterministic verification infrastructure for AI-written software. It runs real programs under declared contracts, records evidence, and produces a bounded PASS/FAIL/INCONCLUSIVE/ERROR result without asking the coding agent to grade its own work. BlindTest makes the boundary concrete: hidden tests exercise the produced program without exposing the suite or oracle to the agent.
B2IGE Verify v0.3.0 is the current public release. The final release record documents its exact-main qualification, platform boundaries, and public asset set.
| Platform | Native archive |
|---|---|
| macOS Apple Silicon | b2ige-0.3.0-aarch64-apple-darwin.tar.gz |
| macOS Intel | b2ige-0.3.0-x86_64-apple-darwin.tar.gz |
| Linux x86_64 | b2ige-0.3.0-x86_64-unknown-linux-gnu.tar.gz |
Also download SHA256SUMS and verify the matching archive before extracting. See installation details for prerequisites and offline validation.
Choose the archive for the host, then verify, extract, and put bin on PATH:
B2IGE_RELEASE_URL=https://github.com/b2ige2-a11y/b2ige-verify/releases/download/v0.3.0
B2IGE_ARCHIVE=b2ige-0.3.0-aarch64-apple-darwin.tar.gz curl -fL -O "$B2IGE_RELEASE_URL/$B2IGE_ARCHIVE" curl -fL -O "$B2IGE_RELEASE_URL/SHA256SUMS"
if command -v shasum >/dev/null 2>&1; then shasum -a 256 "$B2IGE_ARCHIVE" # compare with SHA256SUMS else sha256sum "$B2IGE_ARCHIVE" # compare with SHA256SUMS fi tar -xzf "$B2IGE_ARCHIVE" cd "${B2IGE_ARCHIVE%.tar.gz}" export PATH="$PWD/bin:$PATH" b2ige --version
The archive is ready for the adoption flow or the product-specific commands. Docker is required for BlindTest; missing prerequisites remain a readiness or non-PASS result.
BlindTest asks: does the produced program actually work? It runs visible checks against a correct and a buggy implementation, then executes sealed hidden cases in an attested Docker boundary. The correct implementation passes, the buggy implementation fails, and the sanitized Agent view is checked for private-value leakage.
From a source checkout or the source archive, with Docker available:
docker pull node:24.18.1-bookworm-slim
scripts/demo-blindtest.sh
The demo performs real execution and records evidence; its output is not canned terminal text. See the BlindTest example for the bounded secrecy boundary and the threat model for its limits.
| Product | Question | What it checks |
|---|---|---|
| BlindTest | Does it actually work? | Sealed hidden tests against an agent-produced target inside the declared Docker boundary. |
| BehaviorSeal | Did it change? | Trusted reference/candidate behavior under equivalent deterministic experiments. |
| SideEffect Proof | Did it actually happen? | Committed local SQLite effects under retries and fault schedules, not inferred attempts. |
inspect → init → prepare → trust approve → doctor → verify ID
prepare is non-authoritative: it discovers inputs and writes a reviewable draft. Trust approval remains an interactive human/trusted-controller decision. doctor reports readiness, not verification. verify ID resolves the approved identity and produces the real, evidence-backed result. Read the adoption guide for the full boundary.
These are committed measurements on the bounded B2IGE Verify Bench v1 corpus, not a claim of exhaustive correctness or a replacement for product evidence.
| Measurement (on the benchmark corpus) | Observed |
|---|---|
| Known bugs detected | 16 / 16 |
| False PASS | 0 |
| False FAIL | 0 |
| Verified reproduction | 16 / 16 |
| Hidden leakage observed | 0 |
| Agent private-value leakage | 0 |
| Mutation adequacy: known benchmark mutants | 2 / 2 |
All numbers above are on the benchmark corpus only. Bounded testing cannot establish complete correctness.
See the measured snapshot and benchmark methodology.
| Platform | Support boundary |
|---|---|
| macOS Apple Silicon | Native release |
| macOS Intel | Native release |
| Linux x86_64 | Native release; Docker and full benchmark CI |
| Windows x64 | Source/build plus bounded CLI smoke only; not VERIFIED_NATIVE |
| Linux arm64 | Deferred |
macOS binaries are unsigned and unnotarized. See installation and platform details for Docker, source-build, and archive boundaries.
Missing evidence cannot become PASS. Models do not assign verdicts. A result is bounded by the declared experiment, evidence, and platform scope.
Read the threat model, contracts, and evidence model before relying on a result.
Use the documentation index for getting started, product guides, trust and architecture, benchmarks, release history, and developer resources. The false PASS report accepts only synthetic or sanitized details; never upload hidden suites, private canaries, raw human evidence, or credentials.
Start with CONTRIBUTING.md, the architecture, and the security policy. Changes to verifier authority, evidence, contracts, or schemas require deliberate review; missing evidence must never be converted into success.
B2IGE Verify is licensed under Apache-2.0. No telemetry, hosted service, or paid API is required. Product names and trademarks are covered separately by TRADEMARKS.md.