Skip to main content

Umbrix MCP Server

Connect your AI assistant directly to live threat intelligence with smart MCP tools optimized for both large and small AI models.

🚀 Quick Start

1. Get Your API Key

Visit umbrix.dev, sign in, and generate an API key from Account Settings.

2. Install & Configure

git clone https://github.com/trvon/umbrix-mcp.git
cd umbrix-mcp
docker build -t umbrix-mcp:latest .

Option B: Python Package

pip install git+https://github.com/trvon/umbrix-mcp.git

3. Configure Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "umbrix": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "UMBRIX_API_KEY",
        "-e", "UMBRIX_API_BASE_URL", 
        "umbrix-mcp:latest"
      ],
      "env": {
        "UMBRIX_API_KEY": "your-api-key-here",
        "UMBRIX_API_BASE_URL": "https://umbrix.dev/api"
      }
    }
  }
}

Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

4. Alternative: Python Installation

If using pip install instead of Docker:

{
  "mcpServers": {
    "umbrix": {
      "command": "python",
      "args": ["-m", "umbrix_mcp"],
      "env": {
        "UMBRIX_API_KEY": "your-api-key-here",
        "UMBRIX_API_BASE_URL": "https://umbrix.dev/api"
      }
    }
  }
}

🤖 Smart MCP Tools

Optimized for all AI model sizes - from GPT-4 to smaller local models.

🎯 Tool Selection Assistant (Perfect for Smaller Models)

  • get_tool_recommendation - 🆕 Describe what you want to research → Get personalized tool suggestions
    • Example: get_tool_recommendation("I want to research APT29") → Suggests best tools for that task

🔍 Discovery & Exploration (Great Starting Points)

  • discover_recent_threats - Start here! Shows latest activity and data overview
  • threat_correlation - Search for any threat entities with simple terms
  • analyze_indicator - Deep analysis of specific IOCs (IPs, domains, hashes)

💬 Natural Language Queries (Enhanced for Small Models)

  • execute_graph_query - 🚀 ENHANCED Smart tool that converts simple patterns to database queries
    • New patterns: "recent threats", "APT29", "192.168.1.1", "ransomware campaigns"
    • Still supports: Advanced Cypher queries for expert users
  • threat_intel_chat - Natural language Q&A about threats with graph context

🎯 Specific Entity Lookups

  • get_threat_actor - Detailed threat actor profiles and attribution
  • get_malware_details - Comprehensive malware analysis from graph database
  • get_campaign_details - In-depth campaign intelligence from verified data
  • get_cve_details - Comprehensive CVE analysis with severity and exploitation status

📊 Advanced Analysis

  • timeline_analysis - Temporal patterns and activity analysis
  • indicator_reputation - Reputation scoring for IOCs
  • network_analysis - Analyze IP ranges and networks
  • threat_actor_attribution - Attribute indicators to actors
  • ioc_validation - Validate and enrich indicators

🛠️ System & Management

  • system_health_check - Verify platform status when other tools fail
  • feed_status - Check threat intelligence feed health
  • user_quota - Monitor usage limits and access controls

🧠 Model Size Optimization

For Smaller Models (Claude 3 Haiku, Local LLMs):

  1. Start with get_tool_recommendation("describe your task")
  2. Use discover_recent_threats for exploration
  3. Try execute_graph_query with simple patterns like "recent threats" or "APT29"

For Larger Models (GPT-4, Claude 3.5 Sonnet):

  • Full access to advanced Cypher queries in execute_graph_query
  • Complex natural language processing in threat_intel_chat
  • Multi-step analysis workflows

Development

# Clone repository
git clone https://github.com/umbrix/umbrix-mcp.git
cd umbrix-mcp

# Install dependencies  
uv install

# Run tests
uv run pytest

# Build Docker image
docker build -t umbrix-mcp:latest .

# Test the server
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | \
  docker run --rm -i -e UMBRIX_API_KEY=test umbrix-mcp:latest

📄 License

MIT License - see LICENSE file for details.


umbrix.dev • Documentation

Metadata

Release files for umbrix-mcp 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for umbrix-mcp 0.2.0
File Size Uploaded Provenance
umbrix_mcp-0.2.0.tar.gz 33.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for umbrix-mcp 0.2.0
File Interpreter ABI Platform
umbrix_mcp-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 56.5 kB

Release files / umbrix_mcp-0.2.0.tar.gz

Download URL umbrix_mcp-0.2.0.tar.gz
Size 33.5 kB
Tags Source
SHA-256 checksum
How to use checksums
c9b9fff0155e5b15533a186e1e8a66d9e260c205d822576a352af155df2b4b5b
BLAKE2b-256 checksum
How to use checksums
b2d001e5d4959183c449cccb3afc33a312e095c9279532a8ad42b3ae36c43876
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.9

Release files / umbrix_mcp-0.2.0-py3-none-any.whl

Download URL umbrix_mcp-0.2.0-py3-none-any.whl
Size 23.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
464fb9ec0054155b0d4081b98232360957d0e78b3b42f5681462e0abf9757b2b
BLAKE2b-256 checksum
How to use checksums
80c86a43ccf461fbbfa0425890d59371a78b6d130dff2ffa98014b92f99967f0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.9

Security for umbrix-mcp 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page