passkey-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@passkey-mcprun myapi -- python app.py"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Passkey
A cross-platform secrets manager for AI coding assistants and CLI tools — stores named credential sets in your system keychain and injects them as environment variables at runtime.
No plaintext secrets in config files. No cloud sync. Protected by your OS keychain's access controls (optional Touch ID / sudo prompt for terminal use).
Features
Store multiple secrets per entry in the system keychain (macOS Keychain, Windows Credential Manager, Linux Secret Service)
Inject secrets as environment variables for subprocesses
Tool-agnostic — works with Claude, Gemini, VS Code, Cursor, OpenCode, Windsurf, Cline, Zed, and more
Interactive fuzzy-search entry picker (arrow keys + type-to-filter)
Tab completion for bash, zsh, and fish
Generate cryptographically secure random secrets (configurable length, guaranteed character diversity)
Templates for popular services (GitHub, AWS, Slack, OpenAI, Stripe, Vercel, PostgreSQL, MySQL)
Share & receive entries via encrypted file + passphrase (no key exchange needed)
Lifecycle tracking —
last_rotatedtimestamps,passkey rotate,passkey doctor --deepImport from Chrome password exports, existing MCP configs, or passkey backups
Encrypted bundle export/import for safe machine-to-machine transfer
Full audit logging with
passkey audit --summaryOS keychain ACL protection, with optional Touch ID / sudo prompt for terminal commands (opt-in via
passkey config require-auth on)Cross-platform: macOS, Linux, Windows
Related MCP server: qring-mcp
Installation
# Recommended: install globally with pipx
pipx install passkey-mcp
# Or with pip
pip install passkey-mcp
# Development mode (from source)
pip install -e .Requirements
Python 3.10+
System keychain access (macOS Keychain, Windows Credential Manager, or a running Linux keyring daemon)
Quick Start
# First run — guided onboarding
passkey
# ┌─────────────────────────────────────────────┐
# │ Welcome to passkey │
# │ Secrets in your keychain. Not in config. │
# └─────────────────────────────────────────────┘
# Create your first entry now? [Y/n]
# Create an entry
passkey new
# Entry name: github
# Field name: GITHUB_TOKEN
# Value: [hidden input]
# List all entries
passkey list
# Run a command with secrets injected
passkey run github -- python app.pyShell Completion
Set up tab completion for your shell:
# Zsh (macOS default)
eval "$(passkey completion --zsh)"
# Bash
eval "$(passkey completion --bash)"
# Fish
passkey completion --fish > ~/.config/fish/completions/passkey.fishAfter setup, tab completion works everywhere:
passkey <TAB> # Show entries + subcommands
passkey hugg<TAB> # Fuzzy-match: huggingface_key
passkey get <TAB> # Complete entry names
passkey run <TAB> # Pick entries to loadInteractive Mode
When you omit an entry name (or type a partial match), passkey shows an interactive picker with fuzzy search:
$ passkey get
? Select entry to browse: (Use arrow keys, type to filter)
❯ github
openai
slack
myapi_read
myapi_write
# Type to filter:
$ passkey get my
# Automatically shows: myapi_read, myapi_write
# Single match auto-selects:
$ passkey get github
Copied 'GITHUB_TOKEN' to clipboard (auto-clears in 30s)
# Shortcut: passkey <entry> opens the picker directly
$ passkey githubFuzzy Matching
Prefix:
mymatchesmyapi_read,myapi_writeContains:
apimatchesmyapi_read,myapi_writeSequence:
ghmatchesgithubCase-insensitive:
GITHUBmatchesgithub
CLI Reference
Entry Management
Command | Description |
| Create a new entry interactively |
| List all entry names |
| Entry names only (one per line, for scripting) |
| Modify an existing entry |
| Delete an entry (exact match required) |
| Show entry metadata and field names |
| Clone an entry under a new name |
| Upsert a single field |
Retrieving Secrets
Command | Description |
| Interactive field picker — select a field to copy |
| Copy all fields to clipboard |
| Shortcut: same as |
Running Commands
# Run with secrets from one entry
passkey run github -- python app.py
# Run with secrets from multiple entries (later entries override)
passkey run aws github -- python deploy.py
# Secrets injected as env vars
passkey run myapi -- curl -H "Authorization: Bearer $API_TOKEN" https://api.example.com/v1/dataTool Integration
# Scan configs and migrate plaintext secrets to keychain
passkey init # Auto-detect all tools
passkey init --tool claude # Specific tool
passkey init --tool vscode
# Restore wrapped configs back to inline commands (the way out)
passkey unwrap # Auto-detect all tools
passkey unwrap --dry-run # Preview first
# Add or update credentials for an MCP server
passkey add my-server # Interactive field entry
passkey add my-server --tool claude # Target a specific tool config
passkey add my-server API_KEY=abc TOKEN=xyz # Non-interactive (KEY=VALUE)
# Show security status across all tools
passkey status
# Run diagnostics
passkey doctor
# List MCP servers across tools
passkey serversSupported tools: claude, claude_desktop, gemini, vscode, cursor, opencode, windsurf, cline, zed
Export and Backup
# Export all entries to file (owner-only permissions set automatically)
passkey export backup.json
# Export specific entries
passkey export backup.json --entries github openai
# Export metadata only (no secret values)
passkey export backup.json --no-secrets
# Encrypted export (AES-256-GCM + scrypt)
passkey export backup.passkey.enc --encryptImport
# Import from passkey backup
passkey import backup.json
# Preview without importing
passkey import backup.json --dry-run
# Handle duplicates: skip (default), overwrite, merge
passkey import backup.json --mode merge
# Import from encrypted bundle
passkey import backup.passkey.enc --decrypt
# Import from Chrome password export (CSV)
passkey import passwords.csv --filter github.com
# Import from an existing MCP config file
passkey import claude_desktop_config.jsonAudit Log
passkey audit # View recent operations
passkey audit --limit 50 # Show more entries
passkey audit --clear # Clear the log
passkey audit --summary # Aggregate statisticsVerify Entry Health
# Exit non-zero if any required fields are missing
passkey check github GITHUB_TOKEN GITHUB_USERNAMEGenerate Secrets
# Generate a 32-char random secret (default)
passkey generate
# Generate with custom length
passkey generate --length 64
# Generate without auto-copying to clipboard
passkey generate --no-copyCredential Templates
# List built-in templates
passkey template list
# Show a template's fields
passkey template show github
# Apply a template to create a new entry
passkey template apply github
# Save a custom template from an existing entry
passkey template add my-service --from myapiShare & Receive
# Share an entry (generates encrypted file + passphrase)
passkey share github --output github-shared.passkey
# Receive a shared entry
passkey receive github-shared.passkeyLifecycle Management
# Mark an entry as rotated (updates last_rotated timestamp)
passkey rotate github
# Run expanded diagnostics
passkey doctor --deepAuthentication
The primary protection for your secrets is the OS keychain's own access control — macOS Keychain, Windows Credential Manager, and Linux Secret Service all gate access per application and may show their own unlock prompts. Passkey relies on that by default, so wrapped MCP servers can start headless (no terminal, no password prompt).
If you want an additional OS-auth prompt for interactive terminal
commands (get, new, edit, export, ...), opt in:
passkey config require-auth onThe tradeoff, explicitly:
Off (default): Anyone with an unlocked session as your user can read secrets via
passkey— same as any other tool reading your keychain (e.g.security find-generic-password). MCP servers work everywhere, including stock macOS with no tty.On: Interactive commands first run
sudo -v(macOS, Touch ID ifpam_tidis configured) orpkexec(Linux). This breaks any non-interactive use of those commands —passkey runis never gated either way, because MCP servers invoke it headless.Windows: the setting is a no-op — UAC cannot authenticate the current process, so protection comes from Credential Manager ACLs alone.
Unwrapping (leaving passkey)
passkey init rewrites your MCP configs to the wrapped form — but it is
not a one-way door. Restore the original inline commands with:
passkey unwrap # all detected tools
passkey unwrap --tool claude # one tool
passkey unwrap --server github # one server
passkey unwrap --restore-secrets # also write secret values back into the config
passkey unwrap --dry-run # preview onlyA .backup of each config is written before changes (init does this too),
so you can also restore by hand.
MCP Config Example
Before (insecure — secret in plaintext):
{
"mcpServers": {
"github": {
"command": "python",
"args": ["-m", "github.server"],
"env": {
"GITHUB_TOKEN": "ghp_PLAINTEXT_SECRET_HERE"
}
}
}
}After (secure — secret loaded from keychain at runtime):
{
"mcpServers": {
"github": {
"command": "passkey",
"args": ["run", "github", "--", "python", "-m", "github.server"]
}
}
}MCP Server Mode
Passkey can run as an MCP server itself, letting AI assistants invoke passkey tools via natural language:
{
"mcpServers": {
"passkey": {
"command": "passkey-mcp-server"
}
}
}Available tools: passkey_list, passkey_fields, passkey_status, passkey_doctor, passkey_wrap_server.
AI assistants can discover entry names but never see secret values — secrets only flow out via passkey run.
Data Storage
Platform | Data directory |
macOS |
|
Linux |
|
Windows |
|
Secrets themselves are stored in the system keychain, not on disk. The data directory holds metadata (lock file, audit log).
Security
Encrypted at rest: System keychain handles encryption (AES-256-GCM on macOS, DPAPI on Windows)
No secrets logged: Only entry names and operation types appear in the audit log
Hidden input:
getpassused for all secret entryClipboard auto-clear: Copied secrets cleared after 30 seconds
Secure export: Files created with
chmod 600(owner-only)Encrypted bundles: AES-256-GCM + scrypt (N=2^20) for portable transfer
LLM-safe: AI assistants can list entries but never read values
See docs/SECURITY.md for full details.
Troubleshooting
"Failed to access Keychain" (macOS)
Grant Terminal / Python keychain access in System Settings → Privacy & Security.
Touch ID not working
Ensure pam_tid.so is configured in /etc/pam.d/sudo:
sudo sed -i '' '2i\
auth sufficient pam_tid.so
' /etc/pam.d/sudoLinux headless / no keyring daemon
Set a backend explicitly:
export PYTHON_KEYRING_BACKEND=keyring.backends.SecretService.Keyring
# or for headless environments:
export PYTHON_KEYRING_BACKEND=keyring.backends.null.KeyringEntry not found
passkey list # check exact names (case-sensitive)Import shows "skipped (exists)"
passkey import backup.json --mode mergeDevelopment
pip install -e ".[dev]"
pytest tests/ -v
ruff check passkey/License
MIT — see LICENSE
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityFmaintenanceA GitHub-native secrets manager that allows AI assistants to securely manage, generate, and validate credentials without exposing sensitive values in conversation history. It supports secret scanning, environment diffing, and secure command execution by injecting masked variables directly into the runtime environment.8112MIT
- AlicenseAqualityAmaintenanceA quantum-inspired secret manager that anchors API keys to your OS-native vault, preventing plaintext .env leaks. It empowers AI agents with advanced mechanics like multi-environment superposition, linked entanglements, and ephemeral in-memory tunneling.4447793AGPL 3.0
- Alicense-qualityDmaintenanceLocal, encrypted credential vault for AI agents that enables secure multi-account management across services like Supabase, GitHub, Vercel, and Stripe, allowing seamless account switching without restarting the chat client.162MIT
- Alicense-qualityDmaintenanceEnables AI agents to securely manage API keys and secrets via the MCP protocol, with encrypted storage at rest and a simple CLI and Python SDK.MIT
Related MCP Connectors
Encrypted secret store and rotation for autonomous agent credentials
Issue, rotate and revoke scoped API-key passes for 25+ providers — the agent never sees a real key
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TheNickSanchez/passkey-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server