SDE

MCP server enabling SD Elements API access for LLMs to manage projects, surveys, scans, diagrams, countermeasures, and reports.
  • typescript

7

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "geoffwhittington-sde-mcp": {
      "command": "uvx",
      "args": [
        "git+https://github.com/geoffwhittington/sde-mcp.git"
      ],
      "env": {
        "SDE_HOST": "https://your-sdelements-instance.com",
        "SDE_API_KEY": "your-api-key-here"
      }
    }
  }
}

You are getting a Model Context Protocol (MCP) server that connects SD Elements data and workflows to your language models. This server enables you to manage SD Elements projects, configurations, surveys, repository scans, diagrams, countermeasures, and advanced reports through natural language and programmable endpoints, making your security development lifecycle automation practical and scalable.

How to use

Use an MCP client to issue natural language commands that drive SD Elements actions through the MCP server. You can create and manage applications and projects, set up project surveys using natural language, automatically populate surveys from repository scans, and track countermeasures and diagrams. You can query current configurations, commit survey drafts, and run advanced reports or cube queries for analytics. Start by connecting your MCP client to one of the available server interfaces, then perform common workflows such as creating an application, creating a project, configuring the project survey with technology names, and committing the survey draft to publish countermeasures.

How to install

Prerequisites: install a modern Python runtime and ensure you can run commands from your shell. You should also have a command runner available to start the MCP server from your environment.

Install and run the MCP server using one of the supported approaches shown below. Choose the option that matches how you prefer to run Python-based tools and how you want to start the server locally.

# Option A: Install via pip and run the server
pip install sde-mcp-server
sde-mcp-server

# Option B: Install from GitHub and run the server
pip install git+https://github.com/geoffwhittington/sde-mcp.git
sde-mcp-server

# Option C: Use uvx to install and run from a git URL
uvx git+https://github.com/geoffwhittington/sde-mcp.git
# Then start the server (if the package exposes a start command via PATH)
# Depending on your setup, you may run the standard start command provided by the package

Configuration and startup options

The server requires two environment variables to connect to your SD Elements instance and authenticate API requests.

SDE_HOST=https://your-sdelements-instance.com
SDE_API_KEY=your-api-key-here

Operational notes

After starting the server, you connect your MCP clients and begin issuing natural language commands. You will manage projects, surveys, repository scans, diagrams, and countermeasures through the MCP interface. If you are using the repository scanning workflow, you can scan a repository to auto-populate the project survey, then commit the survey draft to publish countermeasures.

Additional usage patterns

  • Set surveys using plain English instead of IDs: e.g., you can specify technologies like Python, Django, PostgreSQL, AWS, and Docker directly.

  • Add or remove specific survey answers incrementally without re-creating the entire survey, and use commit to publish the draft when ready.

  • Manage countermeasures by listing, updating status, or adding notes. Notes are saved in conjunction with status changes or via a dedicated note tool when appropriate.

Security and best practices

Always protect your SD Elements API key. Store credentials securely (e.g., environment variables or secret managers) and avoid exposing them in logs or shared configurations.

Troubleshooting

If the MCP server fails to start, verify that SDE_HOST and SDE_API_KEY are correctly set in your environment. Check that the Python runtime is 3.10 or higher and that you are using a compatible command runner. If you encounter authentication errors, regenerate or verify your API token in your SD Elements settings.

Complete example workflows

Project setup and survey configuration can be combined into a smooth flow using the MCP client. Create an application, create a project, set the survey with the desired technologies, and commit the survey draft to publish countermeasures. Use repository scanning to auto-detect technologies and populate the survey, then review and commit changes.

Available tools

list_projects

List all projects with optional filtering

get_project

Get detailed information for a specific project

create_project

Create a new SD Elements project

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational