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)
MCP server for the Frame security scanner: scan, verify, fix, exploit, packs and separation logic.
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。
FRAME_LLM_BASE_URL, FRAME_LLM_API_KEY, FRAME_LLM_MODEL标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
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": {
"frame": {
"command": "uvx",
"args": [
"frame-mcp"
],
"env": {
"FRAME_LLM_BASE_URL": "your-value",
"FRAME_LLM_API_KEY": "your-value",
"FRAME_LLM_MODEL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add frame --env FRAME_LLM_BASE_URL=your-value --env FRAME_LLM_API_KEY=your-value --env FRAME_LLM_MODEL=your-value -- uvx frame-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"frame": {
"command": "uvx",
"args": [
"frame-mcp"
],
"env": {
"FRAME_LLM_BASE_URL": "your-value",
"FRAME_LLM_API_KEY": "your-value",
"FRAME_LLM_MODEL": "your-value"
}
}
}
}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": {
"frame": {
"type": "stdio",
"command": "uvx",
"args": [
"frame-mcp"
],
"env": {
"FRAME_LLM_BASE_URL": "your-value",
"FRAME_LLM_API_KEY": "your-value",
"FRAME_LLM_MODEL": "your-value"
}
}
}
}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。
FRAME_LLM_BASE_URL envFRAME_LLM_MODEL env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 lambdasec 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。
你需要填写:FRAME_LLM_API_KEY
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(0.2.0)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 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Detailing Manager
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.
Connect your auto detailing studio's tasks, cars, clients and revenue to Claude or ChatGPT.
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.lambdasec/frame-mcp
An MCP server that exposes the Frame security scanner to any MCP client, so a coding agent can scan code, verify fixes, and reason about vulnerabilities over stdio.
Frame combines taint analysis with separation logic verification to find data-flow vulnerabilities (SQL injection, command injection, path traversal, and more), and checks each reported path with a solver. This package wraps the frame command line program as MCP tools. It launches frame as a subprocess with an explicit argument list, never a shell, and prefers the frame executable installed next to the running Python interpreter.
Run directly with uvx (no separate install step):
uvx frame-mcp
claude mcp add frame -- uvx frame-mcp
Add this stanza to ~/.codex/config.toml:
[mcp_servers.frame]
command = "uvx" args = ["frame-mcp"]
Create .cursor/mcp.json:
{
"mcpServers": { "frame": { "command": "uvx", "args": ["frame-mcp"] } } }
Create .vscode/mcp.json:
{
"servers": { "frame": { "type": "stdio", "command": "uvx", "args": ["frame-mcp"] } } }
Add to ~/.codeium/windsurf/mcp_config.json under the mcpServers key:
{
"mcpServers": { "frame": { "command": "uvx", "args": ["frame-mcp"] } } }
Add to ~/.gemini/settings.json under the mcpServers key:
{
"mcpServers": { "frame": { "command": "uvx", "args": ["frame-mcp"] } } }
Add to Zed settings.json under context_servers:
{
"context_servers": { "frame": { "command": { "path": "uvx", "args": ["frame-mcp"] } } } }
| Tool | Purpose | Read only | |
|---|---|---|---|
scan | Scan a file or directory for vulnerabilities and return findings as JSON; ai adds LLM detection and triage, hunt_authz the agentic authorization hunt. | yes | |
write_baseline | Scan a path and record the findings as a baseline file. | no | |
verify | Re-scan the files behind earlier findings and report whether each is fixed. | yes | |
fix | Generate and verify fixes for findings. Returns a diff by default. | no | |
exploit | Drive an agent to exploit a live, authorized target. | no | |
packs_list | List the framework packs a scan would load. | yes | |
packs_check | Validate framework pack files. | yes | |
solve | Check a separation logic entailment `P \ | - Q`. | yes |
A security-review prompt chains scan (with the AI layer), verify, and an offer to fix.
The scan tool with ai=true, along with fix and exploit, call an LLM through an OpenAI-compatible endpoint. Configure it with these environment variables in the MCP client that launches the server:
| Variable | Purpose |
|---|---|
FRAME_LLM_BASE_URL | Base URL of the LLM endpoint, for example a local server or a hosted API. |
FRAME_LLM_API_KEY | API key for the endpoint, when it requires one. |
FRAME_LLM_MODEL | Model name to request. |
These are inherited from the server process environment and forwarded to each frame subprocess. Every other setting (streaming, timeouts, agent budgets, the hunt's budgets) is a key of the [llm] / [hunt] tables in the project's .frame.toml, which each frame command reads. The plain scan (taint analysis plus verification) needs none of them.
The exploit tool drives an autonomous agent that sends live traffic to a target. Run it only against systems you own or are explicitly authorized to test. Unauthorized testing of systems you do not control may be illegal.
Apache-2.0. See LICENSE.