Skip to main content

Auth proxy that forwards MCP tool calls to a remote NordStellar MCP server

Project description

NordStellar MCP

Connect any MCP-compatible AI assistant to NordStellar so you can query your platform data directly from chat.

What you get

  • Use natural language to ask about NordStellar data
  • No need to switch to the NordStellar UI or write GraphQL by hand
  • Secure login via your NordStellar account

Setup

1. Add to your MCP client

Add the NordStellar MCP server to your AI assistant’s MCP configuration (e.g. mcp.json or the equivalent in your client):

{
  "nordstellar-mcp": {
    "command": "uvx",
    "args": [
      "nordstellar-mcp",
      "https://platform-mcp.nordstellar.com/mcp"
    ]
  }
}

uvx pulls the nordstellar-mcp package from PyPI. To pin a version, use e.g. "--from", "nordstellar-mcp==0.1.3" before the tool name in args.

To run the same from a shell:

uvx nordstellar-mcp https://platform-mcp.nordstellar.com/mcp

The default endpoint is https://platform-mcp.nordstellar.com/mcp. Contact your NordStellar administrator if you need a different URL.

2. First-time login

When you first use NordStellar, a browser window will open. Sign in with your NordStellar credentials. After that, you’re set—the connection stays authenticated until you sign out or the session expires.

3. Start using it

Ask your AI assistant things like “What projects do I have?” or “Show me recent activity” and it will use your NordStellar data to answer.

4. Install agent skills (optional)

You can install bundled skills the same way as other npx skills add workflows (for example the Google Workspace CLI repo):

# Install all skills at once
npx skills add https://github.com/NordStellar/nordstellar-mcp

# Or pick only what you need
npx skills add https://github.com/NordStellar/nordstellar-mcp/tree/main/skills/nordstellar-general
npx skills add https://github.com/NordStellar/nordstellar-mcp/tree/main/skills/attack-surface-management
npx skills add https://github.com/NordStellar/nordstellar-mcp/tree/main/skills/dark-web-search
npx skills add https://github.com/NordStellar/nordstellar-mcp/tree/main/skills/domain-squatting
npx skills add https://github.com/NordStellar/nordstellar-mcp/tree/main/skills/malware-infection-analysis

Credential storage

Session cookies are saved in your OS credential store under the service name NordStellar MCP:

  • macOS — Keychain
  • Windows — Credential Locker
  • Linux — Freedesktop Secret Service (for example GNOME Keyring or KWallet)

If no secure credential store is available, the proxy keeps credentials in memory only. In that mode, credentials are lost when the process exits.

Any application running as your user account may be able to read stored credentials through the OS credential APIs. This is the standard behavior for desktop credential stores.

Clear stored credentials

To remove stored session cookies, use one of the following:

  • Any platform: run nordstellar-mcp --logout
  • macOS: run security delete-generic-password -s "NordStellar MCP"
  • Windows: remove the Generic Credential named NordStellar MCP from Credential Manager
  • Linux: remove the NordStellar MCP secret from your Secret Service keyring (for example with Seahorse or KWallet Manager)

Requirements

  • uv installed (curl -LsSf https://astral.sh/uv/install.sh | sh)
  • Python 3.10 or newer (uv handles this automatically)
  • keyring — installed automatically as a dependency. Provides persistent, secure credential storage using each platform's native backend:
    • macOS — Keychain
    • Windows — Credential Locker
    • Linux — Freedesktop Secret Service (GNOME Keyring / KWallet). Requires gnome-keyring or kwallet to be available; on headless systems, see the keyring docs for setup instructions.

Community

Need help?

Contact your NordStellar administrator for the correct MCP endpoint URL and any access questions.

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

nordstellar_mcp-0.1.4.tar.gz (33.0 kB view details)

Uploaded Source

Built Distribution

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

nordstellar_mcp-0.1.4-py3-none-any.whl (38.7 kB view details)

Uploaded Python 3

File details

Details for the file nordstellar_mcp-0.1.4.tar.gz.

File metadata

  • Download URL: nordstellar_mcp-0.1.4.tar.gz
  • Upload date:
  • Size: 33.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nordstellar_mcp-0.1.4.tar.gz
Algorithm Hash digest
SHA256 49ad27a79d6f8c994bdd1855bc30b9504373ba947028a6442faf0a87a56e538f
MD5 5e57f333fca5546ceef60d6f0ad57e7d
BLAKE2b-256 8f9e71326dfca4468f2c3254cd58d0b6272ec875f07315165c2b2a69730c3c3f

See more details on using hashes here.

Provenance

The following attestation bundles were made for nordstellar_mcp-0.1.4.tar.gz:

Publisher: publish-pypi.yml on NordStellar/nordstellar-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nordstellar_mcp-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for nordstellar_mcp-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 a4a2679bebd2c027d72fa3674dc687a4afab0f08331ba9c43572b471eb712c0e
MD5 978afa2d94134b7798be3928f2dd4679
BLAKE2b-256 6d478f17223d66ca2c8a76cc34ebd850c02a6a99f1a0aebe2c1ceb549c848bf2

See more details on using hashes here.

Provenance

The following attestation bundles were made for nordstellar_mcp-0.1.4-py3-none-any.whl:

Publisher: publish-pypi.yml on NordStellar/nordstellar-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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