
Devici MCP Server
Provides LLM tools to interact with the Devici API, enabling management of threat modeling resources including users, collections, threat models, components, threats, mitigations, and teams.
Tools
get_users
Get users from Devici with pagination
get_user
Get a specific user by ID
search_users
Search users by field and text
invite_user
Invite a new user to Devici
get_collections
Get collections from Devici with pagination
get_collection
Get a specific collection by ID
create_collection
Create a new collection
get_threat_models
Get threat models from Devici with pagination
get_threat_models_by_collection
Get threat models for a specific collection
get_threat_model
Get a specific threat model by ID
create_threat_model
Create a new threat model
get_components
Get components from Devici with pagination
get_component
Get a specific component by ID
get_components_by_canvas
Get components for a specific canvas
get_threat
Get a specific threat by ID
get_threats_by_component
Get threats for a specific component
get_mitigations
Get mitigations from Devici with pagination
get_mitigation
Get a specific mitigation by ID
get_mitigations_by_threat
Get mitigations for a specific threat
get_teams
Get teams from Devici with pagination
get_team
Get a specific team by ID
get_dashboard_types
Get available dashboard chart types
get_dashboard_data
Get dashboard data for a specific chart type
get_threats
Get threats from Devici with pagination
get_threat_models_report
Get threat models report data
README
Devici MCP Server
A Model Context Protocol (MCP) server for interacting with the Devici API. This server provides LLM tools to manage users, collections, threat models, components, threats, mitigations, teams, and dashboard data through the Devici platform.
Features
The Devici MCP Server provides tools for:
User Management
- Get users with pagination
- Get specific user by ID
- Search users by field and text
- Invite new users
Collections Management
- Get collections with pagination
- Get specific collection by ID
- Create new collections
Threat Models Management
- Get all threat models with pagination
- Get threat models by collection
- Get specific threat model by ID
- Create new threat models
Components Management
- Get components with pagination
- Get specific component by ID
- Get components by canvas
- Create new components
Threats Management
- Get threats with pagination
- Get specific threat by ID
- Get threats by component
- Create new threats
Mitigations Management
- Get mitigations with pagination
- Get specific mitigation by ID
- Get mitigations by threat
- Create new mitigations
Teams Management
- Get teams with pagination
- Get specific team by ID
- Get team users
- Create new teams
Dashboard & Reports
- Get dashboard data
- Get report data
- Get threat model statistics
Comments & Audit
- Get comments with pagination
- Get specific comment by ID
- Get audit logs
Codex Integration
- Get codex attributes
- Get codex mitigations
- Get codex threats
Quick Start
Using uvx (recommended)
Option 1: From GitHub (Current)
uvx git+https://github.com/geoffwhittington/devici-mcp.git
Option 2: From PyPI (Future - when published)
uvx devici-mcp-server
Using uv
Install from GitHub
uv pip install git+https://github.com/geoffwhittington/devici-mcp.git
devici-mcp-server
Install from PyPI (when available)
uv pip install devici-mcp-server
devici-mcp-server
Using pip
Install from GitHub
pip install git+https://github.com/geoffwhittington/devici-mcp.git
devici-mcp-server
Install from PyPI (when available)
pip install devici-mcp-server
devici-mcp-server
Configuration
The server requires three environment variables:
DEVICI_API_BASE_URL
: Your Devici instance URL (e.g.,https://api.devici.com/v1
)DEVICI_CLIENT_ID
: Your Devici client IDDEVICI_CLIENT_SECRET
: Your Devici client secret
Setting Environment Variables
Option 1: Environment Variables
export DEVICI_API_BASE_URL="https://api.devici.com/v1"
export DEVICI_CLIENT_ID="your-client-id-here"
export DEVICI_CLIENT_SECRET="your-client-secret-here"
Option 2: .env File
Create a .env
file in your working directory:
DEVICI_API_BASE_URL=https://api.devici.com/v1
DEVICI_CLIENT_ID=your-client-id-here
DEVICI_CLIENT_SECRET=your-client-secret-here
Getting Your API Credentials
- Log into your Devici instance
- Go to Settings > API Access
- Generate a new client ID and secret
- Copy the values for use as
DEVICI_CLIENT_ID
andDEVICI_CLIENT_SECRET
MCP Client Configuration
Claude Desktop
Add this to your Claude Desktop configuration file:
Option 1: From GitHub (Current)
{
"mcpServers": {
"devici": {
"command": "uvx",
"args": ["git+https://github.com/geoffwhittington/devici-mcp.git"],
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Option 2: From PyPI (Future)
{
"mcpServers": {
"devici": {
"command": "uvx",
"args": ["devici-mcp-server"],
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Cline
Add this to your Cline MCP settings:
From GitHub (Current)
{
"mcpServers": {
"devici": {
"command": "uvx",
"args": ["git+https://github.com/geoffwhittington/devici-mcp.git"],
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Continue
Add this to your Continue configuration:
From GitHub (Current)
{
"mcpServers": {
"devici": {
"command": "uvx",
"args": ["git+https://github.com/geoffwhittington/devici-mcp.git"],
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/api/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Cursor
Add this to your Cursor configuration file:
Option 1: From GitHub (Current)
{
"mcpServers": {
"devici": {
"command": "uvx",
"args": ["git+https://github.com/geoffwhittington/devici-mcp.git"],
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/api/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Option 2: Using local installation
If you have the package installed locally:
{
"mcpServers": {
"devici": {
"command": "devici-mcp-server",
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/api/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Option 3: Using Python module directly
{
"mcpServers": {
"devici": {
"command": "python",
"args": ["-m", "devici_mcp_server"],
"env": {
"DEVICI_API_BASE_URL": "https://api.devici.com/api/v1",
"DEVICI_CLIENT_ID": "your-client-id-here",
"DEVICI_CLIENT_SECRET": "your-client-secret-here"
}
}
}
}
Development
Prerequisites
- uv installed
- Python 3.10 or higher
Setup
# Clone the repository
git clone <repository-url>
cd devici-mcp
# Create virtual environment and install dependencies
uv sync
# Run in development mode
uv run python -m devici_mcp_server
Testing
# Run the import test
uv run python test_basic.py
# Test with environment variables
DEVICI_API_BASE_URL=https://api.devici.com/api/v1 DEVICI_CLIENT_ID=test DEVICI_CLIENT_SECRET=test uv run python -m devici_mcp_server
Building
# Build the package
uv build
# Install locally for testing
uv pip install dist/*.whl
Features
- Full API Coverage: Supports all major Devici API endpoints
- Authentication: Secure client ID/secret-based authentication
- Error Handling: Comprehensive error handling and validation
- Environment Configuration: Flexible configuration via environment variables
- Modern Python: Built with modern Python packaging (uv, pyproject.toml)
- MCP Compliant: Fully compatible with the Model Context Protocol
API Coverage
This server provides access to:
- Users and Teams
- Collections and Threat Models
- Components and Threats
- Mitigations and Comments
- Dashboard Data and Reports
- Audit Logs and Codex Integration
- Search and Bulk Operations
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
Support
For issues and questions:
- Check the Issues page
- Review the Devici API documentation
- Ensure your API credentials have proper permissions
Note: This is an unofficial MCP server for Devici. For official Devici support, please contact the Devici team.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.