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)
Trust metadata for AI agents — check files before building on them, stamp verified work.
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": {
"akf": {
"command": "uvx",
"args": [
"mcp-server-akf"
]
}
}
}在终端中运行这条命令
claude mcp add akf -- uvx mcp-server-akf粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"akf": {
"command": "uvx",
"args": [
"mcp-server-akf"
]
}
}
}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": {
"akf": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-server-akf"
]
}
}
}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 HMAKT99 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(1.6.2)于14天前进入注册中心。
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 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Date Math
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.
Exact date/time math for agents: business days, holidays, time zones, cron, RRULE, SLA. x402 paid.
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。
mcp-name: io.github.HMAKT99/akf
MCP (Model Context Protocol) server that exposes 10 AKF tools to AI agents. Any MCP-compatible client (Claude Desktop, Claude Code, Cursor, Windsurf, etc.) can check, stamp, validate, audit, and scan files using the Agent Knowledge Format.
A stamp costs ~15 tokens. Re-verifying costs 15,000. Agents stamp what they verify; the next agent calls check_file and builds on it instead of redoing the work.
pip install mcp-server-akf
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": { "akf": { "command": "python", "args": ["-m", "mcp_server_akf"] } } }
Add to .cursor/mcp.json in your project root:
{
"mcpServers": { "akf": { "command": "python", "args": ["-m", "mcp_server_akf"] } } }
| Tool | Description |
|---|---|
check_file | One-line trust check — can an agent build on this file without re-verifying? (OK / LOW / STALE / UNSTAMPED) |
create_claim | Create an AKF claim with trust metadata |
validate_file | Validate an .akf file against the spec |
scan_file | Security scan any file for AKF metadata |
trust_score | Compute effective trust score for a claim |
stamp_file | Stamp trust metadata onto any file (20+ formats) |
audit_file | Compliance audit (EU AI Act, SOX, HIPAA, GDPR, NIST, ISO 42001) |
embed_file | Embed AKF metadata into DOCX, PDF, HTML, images, etc. |
extract_file | Extract AKF metadata from any supported format |
detect_threats | Run 10 AI-specific security detections |
Once configured, ask your AI agent:
"Stamp
report.docxwith AKF trust metadata, confidence 0.9, evidence 'quarterly review complete'"
The agent will call stamp_file through MCP and attach provenance automatically.
You can also run the server directly for testing:
python -m mcp_server_akf
On mcp 2.x, a tool result for a file (any tool called with path) carries that file's verification state in _meta under the vendor key dev.akf/trust:
"_meta": {
"dev.akf/trust": { "v": "1", "status": "OK", "trust": 0.7447, "evidence": ["human_review"], "agent": "claude-code", "age_days": 4 } }
status is computed live (OK / LOW / STALE / UNSTAMPED), so a client sees whether the file changed since it was verified. The key is absent when the result isn't about a file. Clients that don't know the key ignore it.
To annotate your own server's results:
from mcp_server_akf.meta import TRUST_META_KEY, trust_meta
meta = trust_meta(path) return CallToolResult(content=[...], _meta={TRUST_META_KEY: meta} if meta else None)
To read it in a client:
result = await client.call_tool("extract_file", {"path": "report.md"})
state = (result.meta or {}).get("dev.akf/trust") if state and state["status"] == "OK": ... # verified and unchanged: build on it without re-verifying
The MCP server works seamlessly with multi-agent orchestration platforms:
akf agent create / akf agent verifyakf agent export-a2aakf certify --team for per-agent trust breakdowns in CISupports: Claude Agent Teams, Copilot Cowork, Codex multi-agent, and any A2A-compatible platform.
akf >= 1.0.0mcp >= 1.0.0