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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.