Skip to main content

MCP server for psamvault — lets AI agents use stored credentials without seeing them.

Project description

psamvault-mcp

MCP server for psamvault — lets AI agents use your stored credentials without ever seeing their plaintext values.

How it works

psamvault exposes two complementary flows depending on what the agent needs.

API request flow (use_credential)

When an AI agent needs to call an API on your behalf, psamvault decrypts the credential locally and forwards the authenticated request through its backend proxy.

The agent never sees the password. It only sees the HTTP response.

Agent: "Call the GitHub API using my stored credential"
         ↓
psamvault shows a consent dialog: "Allow agent to use github.com credential?"
         ↓ (you approve)
psamvault decrypts credential locally using your Vault Encryption Key
         ↓
psamvault makes: GET https://api.github.com/user
                 Authorization: Bearer <your token>
         ↓
Agent receives: {"login": "yourusername", "id": 12345, ...}

Browser login flow (browser_login)

When an AI agent needs to log you into a website, psamvault opens a real Chromium browser, navigates to the site, and fills in the credentials directly inside that browser process.

The agent never sees the credentials. It only sees whether the login succeeded.

Agent: "Log me into kaggle.com"
         ↓
psamvault opens Chromium → navigates to kaggle.com → finds the login page
         ↓
psamvault takes a screenshot of the confirmed login page
         ↓
psamvault shows a consent dialog with the confirmed login URL
         ↓ (you approve)
psamvault decrypts credential locally
         ↓
psamvault fills username + password fields directly in the browser
         ↓
If a CAPTCHA appears, psamvault takes a screenshot, pauses automation,
and tells you to solve the CAPTCHA and click Sign in manually
         ↓
Agent receives:
         {
           "success": true,
           "message": "Logged in to github.com successfully. The browser is open.",
           "steps_count": 8,
           "url": "https://github.com/dashboard",
           "captcha_detected": false,
           "captcha_screenshot": null,
           "failed_at": null,
           "hint": null
         }
         ↓
Browser stays open — you take over from there.
The browser session is saved and reused on subsequent calls to the same site.

Prerequisites

  • Python ≥ 3.11
  • psamvault installed and logged in
pipx install psamvault
psamvault configure
psamvault login

Installation

pipx install psamvault-mcp
playwright install chromium

Goose setup (recommended)

Goose is an open-source AI agent with native MCP support. There are three ways to add psamvault-mcp as a Goose extension:


Option A — One-click deeplink

Click or paste this URL into your browser while Goose Desktop is running:

goose://extension?cmd=psamvault-mcp&timeout=300&id=psamvault&name=psamVault&description=Use%20stored%20credentials%20without%20exposing%20them%20to%20the%20agent

Goose will prompt you to confirm, then the extension is added instantly.


Option B — Goose Desktop UI

  1. Open Goose Desktop.

  2. Click the sidebar button (top-left) → Extensions.

  3. Click Add custom extension.

  4. Fill in the form:

    Field Value
    Type Standard IO
    ID psamvault
    Name psamVault
    Description Use stored credentials without exposing them to the agent
    Command psamvault-mcp
    Timeout 300
  5. Click Add.

The extension appears in your Extensions list — toggle it on to activate it.


Option C — Config file (advanced)

Edit ~/.config/goose/config.yaml and add the following under extensions::

extensions:
  psamvault:
    name: psamVault
    cmd: psamvault-mcp
    args: []
    enabled: true
    type: stdio
    timeout: 300

Save the file and restart Goose (or reload the session).


Verifying the extension works

Once added, start a Goose session and try:

What credentials do I have stored in my vault?

Goose will call list_vault_sites via psamvault-mcp. If you see your stored sites, everything is working.


Other MCP clients

Claude Desktop — config file location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "psamvault": {
      "command": "psamvault-mcp"
    }
  }
}

Restart your MCP client after saving.

Configuration

psamvault-mcp reads its backend URL from ~/.psamvault/config.env, written automatically by psamvault configure.

Variable Default Description
PSAMVAULT_API_URL https://psam-vault-backend.onrender.com psamvault backend endpoint
PSAMVAULT_LOG_LEVEL INFO Log verbosity. Accepts any standard Python level: DEBUG, INFO, WARNING, ERROR. Logs go to stderr.

To point at a self-hosted backend, set the variable in ~/.psamvault/config.env:

PSAMVAULT_API_URL=https://your-backend.example.com

Available tools

Tool Description
get_version Return the installed psamvault-mcp version. No session or login required
search_vault_tools Discover which tool to use — call this first; accepts a keyword or empty string for all tools
list_vault_sites List stored site names (no passwords)
check_credential_exists Check if a credential exists for a site
use_credential Make an authenticated HTTP request
get_username_for_site Get username only (not password)
browser_login Open a real browser and log into a website — credentials filled silently, never shown to the agent

Injection modes

Mode Header format Use case
bearer_token Authorization: Bearer <password> GitHub, OpenAI, most APIs
api_key_header <custom-header>: <password> APIs with X-API-Key headers
basic_auth Authorization: Basic base64(user:pass) HTTP basic auth

Example agent prompts

Once connected, you can ask your agent things like:

  • "What credentials do I have stored in my vault?"
  • "Check my GitHub notifications using my stored github.com credential"
  • "List my AWS S3 buckets using my stored aws credential"
  • "Log me into kaggle.com"
  • "Open github.com and log me in"

Testing

# From the repo root
pytest

Tests live in tests/ and cover crypto primitives, session management, consent logic, the API client (with httpx mocking), and MCP tool behaviour. The test suite requires no real network access or OS keychain — all external dependencies are mocked.

Security

  • Credentials are decrypted locally on your machine — never sent to the agent
  • Every credential use requires explicit approval via a consent dialog
  • The agent only receives HTTP responses, never credential values
  • All communication with the psamvault backend uses HTTPS

License

MIT — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

psamvault_mcp-0.3.0.tar.gz (50.0 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

psamvault_mcp-0.3.0-py3-none-any.whl (30.1 kB view details)

Uploaded Python 3

File details

Details for the file psamvault_mcp-0.3.0.tar.gz.

File metadata

  • Download URL: psamvault_mcp-0.3.0.tar.gz
  • Upload date:
  • Size: 50.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for psamvault_mcp-0.3.0.tar.gz
Algorithm Hash digest
SHA256 994234e6e05150317981f8b38758dfa1fffc6d3a328318c7ec01fc0c7297a886
MD5 ea9a7bdb75d300b7d9479f9aa57eb395
BLAKE2b-256 63265465560fe3b58d41c83265dab5d0fac89c30276268fbd2271fba5fac1d37

See more details on using hashes here.

File details

Details for the file psamvault_mcp-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: psamvault_mcp-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 30.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.0

File hashes

Hashes for psamvault_mcp-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0f99b456ca0365ea3956404fa281125b3d54b9ac95df8c981e01015bc0bb0ca0
MD5 7be2e410eb544993f6b8aec661e7c480
BLAKE2b-256 30f8f0549bf5b6b79aeb56a466f1902ae70cc948a7d2d182f5e3e5461d88819b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page