Skip to main content
Glama
daniel-brenner-fnt

Dependency-Track MCP Server

Dependency-Track MCP Server

A small Model Context Protocol (MCP) server for OWASP Dependency-Track. It exposes a practical subset of the official Dependency-Track REST API over stdio so tools like Codex can query projects, fetch findings, trigger analysis, upload CycloneDX BOMs, and check async token status.

The implementation is based on the official Dependency-Track API surface:

  • GET /api/v1/project

  • GET /api/v1/project/{uuid}

  • GET /api/v1/project/lookup

  • GET /api/v1/project/latest/{name}

  • GET /api/v1/finding/project/{uuid}

  • POST /api/v1/finding/project/{uuid}/analyze

  • PUT /api/v1/bom

  • GET /api/v1/event/token/{uuid}

Official references:

Features

  • list_projects

  • search_projects_by_name

  • get_project

  • lookup_project

  • get_latest_project

  • get_project_findings

  • trigger_project_analysis

  • upload_bom

  • get_event_token_status

Related MCP server: YaTracker Connector

Requirements

  • Node.js 18+ (tested with Node 25)

  • A reachable Dependency-Track instance

  • Either an API key or bearer token with the necessary Dependency-Track permissions

Configuration

Set these environment variables before starting the server:

$env:DEPENDENCY_TRACK_BASE_URL="https://dependency-track.example.com"
$env:DEPENDENCY_TRACK_API_KEY="your-api-key"

Or use a bearer token instead:

$env:DEPENDENCY_TRACK_BASE_URL="https://dependency-track.example.com"
$env:DEPENDENCY_TRACK_BEARER_TOKEN="your-bearer-token"

Run

node src/index.js

Codex MCP configuration

Example stdio entry:

{
  "mcpServers": {
    "dependency-track": {
      "command": "node",
      "args": [
        "C:/absolute/path/to/dependency-track-mcp-server/src/index.js"
      ],
      "env": {
        "DEPENDENCY_TRACK_BASE_URL": "https://dependency-track.example.com",
        "DEPENDENCY_TRACK_API_KEY": "your-api-key"
      }
    }
  }
}

Notes on permissions

The server only wraps official Dependency-Track endpoints. Actual access still depends on the permissions of the API key or bearer token:

  • project listing and lookup: VIEW_PORTFOLIO

  • findings and analysis: VIEW_VULNERABILITY

  • BOM upload: BOM_UPLOAD

  • auto-create during BOM upload: PORTFOLIO_MANAGEMENT or PROJECT_CREATION_UPLOAD

Query behavior

  • list_projects now supports optional client-side offset and limit parameters.

  • search_projects_by_name is intended for normal interactive use and defaults to returning up to 25 matches.

  • Both tools still use the official GET /api/v1/project endpoint underneath.

License

MIT

A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/daniel-brenner-fnt/dependency-track-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server