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)
Tamper-evident evidence log of agent changes, scans and approvals, mapped to ISO 27001/NIS2.
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。
你需要
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"evidence": {
"command": "npx",
"args": [
"-y",
"@tollwire/evidence-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add evidence -- npx -y @tollwire/evidence-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"evidence": {
"command": "npx",
"args": [
"-y",
"@tollwire/evidence-mcp"
]
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"evidence": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tollwire/evidence-mcp"
]
}
}
}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8日
注册名称已通过 GitHub 账户 TollWire 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(0.1.2)于昨天进入注册中心。
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 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Tethered Trust
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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.
Fit, compatibility and recall checks for AI agents before they buy: verdicts, evidence, receipts.
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。
tollwire-evidence, MVP)MCP server that records agent changes, reviews, scans, approvals, deployments, incidents and permission changes as a tamper-evident hash chain. It maps event types to ISO/IEC 27001:2022 Annex A and NIS2 Article 21(2) controls (draft).
Status: version 0.x (MVP). Interfaces can change incompatibly before 1.0. Installation, the marketplace and npm options, and the project-wide security notes are in the top-level README. Issues are welcome; pull requests from third parties are not accepted, see CONTRIBUTING.md.
| Tool | Purpose |
|---|---|
record_event | Append an event. Events that contain a recognized secret format are refused. Type anchor is accepted only with a matching anchor (see below). |
list_events | Read events, optionally filtered by type. |
verify_log | Check the hash chain. Also checks the local anchor file (if present) and any external anchors passed in anchors. |
create_anchor | Write the last entry as an anchor {seq, hash, ts, count} to the anchor file. Returns the anchor line, a tag name and a suggested signed Git tag command. Writes no event. |
map_controls | Map event types to controls (draft, not confirmed by an auditor). |
export_report | Markdown evidence report with integrity and coverage. |
TOLLGATE_EVIDENCE_LOG if set; otherwise .tollgate/evidence/log.jsonl in the project directory (CLAUDE_PROJECT_DIR, or the current directory). .anchors.jsonl in the same directory. Append-only. Each line carries prev_anchor_hash and anchor_hash, so the anchor file is itself tamper-evident.An anchor records the sequence number, hash, timestamp and count of the last entry in canonical JSON, for example {"count":42,"hash":"…","seq":42,"ts":"2026-10-04T08:00:00.000Z"}.
verify_log checks, besides the chain, that for each anchor an entry with that seq exists and carries exactly that hash and timestamp. A log that was rewritten after the anchor (a new, internally valid chain) or truncated is then detected.
valid means only "internally consistent".anchored is true only if the result is valid and at least one external anchor was confirmed. valid: true with anchored: false is not proof that the log is unchanged.Recommended procedure, performed by a person with their own signing key:
create_anchor (or node scripts/anchor.mjs create in the package directory).anchor event with node scripts/anchor.mjs record ' ' signed_tag . Exit code 0: recorded. Exit code 2: refused.Verification: git tag -v checks the signature. Then pass the anchor line from the tag message to verify_log (anchors), or run node scripts/anchor.mjs verify ' ' (exit 0 valid, 1 finding, 2 usage error).
anchor eventsAn anchor event documents that a person stored an anchor outside the machine. The control mapping is a draft (ISO/IEC 27001:2022 A.8.15, A.5.33, A.5.28; NIS2 Article 21(2)(f)).
create_anchor, then the external storage, then the anchor event. Recording the event before storage would document a storage that has not happened yet.ref (tag name or comment URL), details.anchor (the stored anchor) and details.storage (signed_tag or digest_comment).seq must have the same hash and timestamp. This is checked under the lock. Otherwise nothing is written.ref points to a real storage location. Only the signed tag or comment itself is evidence of that.The hash chain shows that the log is internally consistent. It does not show who wrote an entry.
actor is free text supplied by the caller. The server does not check identity. Any process that may write the log can record any actor, including the name of a person.anchor event is also self-declared. Only the external storage itself is evidence.anchor events in the log.record_event refuses events whose content matches a known credential format: private keys (PEM, OpenSSH, PGP), GitHub, GitLab and npm tokens, AWS access keys, Anthropic and OpenAI keys (sk-…), Stripe keys (sk_live_, sk_test_, rk_…), Google API keys (AIza…), signed JWTs, Slack tokens and Slack webhook URLs. Only formats with a fixed prefix are recognized, which keeps false positives low. Unknown formats and freely chosen passwords are not detected. Do not put secrets into events.
The files field of package.json includes dist/, .claude-plugin/, .mcp.json, scripts/anchor.mjs, LICENSE and README.md. Source code, tests, coverage and the smoke test are not shipped. Run npm run build before packing, so that no stale files are included.
verify_log. Entries after the last anchor are not protected.npm ci --ignore-scripts
npm run check # typecheck, lint, tests with coverage, build, smoke test
Node.js 22.12.0 or later is required (engines). Runtime dependency: zod only, pinned to an exact version.
Dependencies and security: the MCP server is a small built-in implementation (src/vendor/mcpStdio.ts): JSON-RPC 2.0 over stdin/stdout, one message per line, protocol versions as in the official SDK 1.32.0 (latest 2025-11-25). It opens no network connection, rejects lines over 1 MiB (the session ends with exit code 1) and the key __proto__, and writes diagnostics to stderr only. The official @modelcontextprotocol/sdk is a development dependency only: scripts/sdkCompat.mjs (part of npm run smoke) connects its Client with StdioClientTransport to the built server and calls every tool. The SDK and its HTTP stack are not installed with the package.
Source-available under the PolyForm Noncommercial License 1.0.0 (SPDX: PolyForm-Noncommercial-1.0.0), see also NOTICE. Noncommercial use only; commercial use requires prior written permission. Details: LEGAL.md.