Package Exports

@devlaws/mcp-server
@devlaws/mcp-server/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@devlaws/mcp-server) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

@devlaws/mcp-server

Connect your AI coding assistants (Claude, Cursor, Codex) to the DevLaws engineering protocol.

The DevLaws Model Context Protocol (MCP) Server bridges your AI coding assistants with your DevLaws active protocols, architectural standards, and engineering laws. It allows your local AI agents to seamlessly read your customized standards, check prompt compliance, and fetch engineering guidelines in real-time as you build. Manage your active standards, collections, and developer API credentials on the official console at tool.devlaws.xyz.

Quick Start & Installation

You can run the server dynamically on the fly using npx (recommended), or install it globally via npm:

npm install -g @devlaws/mcp-server

Configuration & Connection

The MCP server connects to the DevLaws mainframe using secure authentication. You must set the following environment variables in your MCP host:

DEVLAWS_EMAIL: The email address associated with your DevLaws account.
DEVLAWS_API_KEY: Your personal developer API Key (generated on your DevLaws Integrations Dashboard).
DEVLAWS_API_URL: (Optional) Overrides the destination API endpoint (defaults to https://api.devlaws.xyz).

Claude Desktop

Add the following to your local configuration (~/.config/Claude/claude_desktop_config.json on macOS/Linux or %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "devlaws": {
      "command": "npx",
      "args": ["-y", "@devlaws/mcp-server"],
      "env": {
        "DEVLAWS_EMAIL": "your-account-email@example.com",
        "DEVLAWS_API_KEY": "dlk_your_api_key_here"
      }
    }
  }
}

Cursor

Open Settings → Features → MCP.
Click + Add New MCP Server.
Configure the following parameters:
- Name: devlaws
- Type: command
- Command: npx -y @devlaws/mcp-server
Set the environment variables:
- DEVLAWS_EMAIL: your-account-email@example.com
- DEVLAWS_API_KEY: dlk_your_api_key_here

OpenAI Codex CLI

codex mcp add devlaws \
  --env DEVLAWS_EMAIL="your-account-email@example.com" \
  --env DEVLAWS_API_KEY="dlk_your_api_key_here" \
  -- npx -y @devlaws/mcp-server

Available MCP Tools (10)

The server exposes the following capabilities to your AI agent:

Tool Name	Description	Authentication Required
`get_laws`	Fetch the list of all engineering laws and standards	No
`search_laws`	Search laws by keyword or topic	No
`get_law_detail`	Retrieve full technical specifications of a law by slug	No
`get_my_profile`	Retrieve your DevLaws user profile information	Yes
`get_protocol`	Fetch your active enforced engineering protocol laws	Yes
`get_bookmarks`	Fetch your saved/bookmarked laws	Yes
`add_to_protocol`	Start enforcing a specific engineering standard	Yes
`remove_from_protocol`	Stop enforcing a specific standard	Yes
`add_bookmark`	Bookmark a law for quick reference	Yes
`remove_bookmark`	Unbookmark a saved law	Yes

Security & Safe-Handling

All communications between the local MCP server and the DevLaws API are encrypted over HTTPS. Never share or commit your DEVLAWS_API_KEY to public repositories. If your key is compromised, regenerate it immediately from your Integrations dashboard.