PhantomAuth
Enables AI agents to securely fill web forms with credentials from SecureVault, keeping raw secrets hidden from the agent.
README
PhantomAuth
MCP server that fills web forms with secrets from SecureVault — AI agents never see raw credentials.
How it works
PhantomAuth sits between your AI agent and Microsoft's Playwright MCP:
AI Agent → PhantomAuth MCP → Playwright MCP → Browser
↕
SecureVault (OS Keychain)
- Agent calls
secure_fill("Microsoft Email", "#email-input") - PhantomAuth resolves "Microsoft Email" from SecureVault's OS keychain
- The raw value is forwarded directly to Playwright MCP's
browser_fill_form - Agent only sees "✅ Filled — value hidden from agent"
The agent never sees the actual password, token, or credential.
Prerequisites
- SecureVault installed with secrets in the OS keychain
- Playwright MCP running in HTTP mode:
npx @playwright/mcp@latest --port 8931 --shared-browser-context
Setup
Add to your MCP client configuration (e.g. VS Code mcp.json):
{
"mcpServers": {
"phantomauth": {
"command": "node",
"args": ["C:/src/PhantomAuth/index.js"],
"env": {
"PLAYWRIGHT_MCP_URL": "http://localhost:8931/mcp"
}
}
}
}
Tools
secure_fill
Fill a form field with a secret. Uses Playwright's fill (sets value directly).
secure_fill(secretTitle: "My Password", selector: "#password")
secure_type
Type a secret into a field keystroke-by-keystroke. Use for React-controlled inputs.
secure_type(secretTitle: "TOTP Code", selector: "#otp-input", pressEnterAfter: true)
secure_authenticate
Multi-step login flow using a SecureVault profile.
secure_authenticate(
profileName: "Microsoft",
steps: [
{ selector: "#email", envVar: "EMAIL", action: "fill" },
{ selector: "#password", envVar: "PASSWORD", action: "fill", pressEnterAfter: true, waitMs: 2000 }
]
)
list_vault_secrets
List available secret names (values are never exposed).
list_vault_profiles
List profiles and their env var → secret mappings.
Configuration
| Environment Variable | Default | Description |
|---|---|---|
PLAYWRIGHT_MCP_URL |
http://localhost:8931/mcp |
URL of the Playwright MCP HTTP endpoint |
License
MIT
AI Agent Skills
PhantomAuth includes instruction files that teach AI agents how to use the tools:
| File | Agent | Description |
|---|---|---|
.github/copilot-instructions.md |
GitHub Copilot | Custom instructions loaded automatically by Copilot |
.claude/skills/phantomauth.md |
Claude Code | Skill file discovered by Claude Code |
SKILL.md |
Universal | Cross-agent skill file (agentskills.io format) |
Using with agentskills CLI
npx agentskills export --target copilot
npx agentskills export --target claude
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。