Enables AI assistants to interact with the Velociraptor DFIR platform.
Megaraptor MCP
A Model Context Protocol (MCP) server that provides AI assistants with access to Velociraptor - the powerful digital forensics and incident response (DFIR) platform.
Overview
Megaraptor MCP enables AI assistants like Claude to interact with Velociraptor servers for:
- Endpoint Management: Search, interrogate, and manage Velociraptor clients
- Artifact Collection: Schedule forensic artifact collection on endpoints
- Threat Hunting: Create and manage hunts across multiple endpoints
- VQL Queries: Execute arbitrary Velociraptor Query Language queries
- Incident Response: Pre-built DFIR workflow prompts for common scenarios
- Deployment Automation: Deploy Velociraptor servers and agents across infrastructure (Docker, binary, cloud, GPO, SSH, WinRM, Ansible)
Features
MCP Tools (33 tools)
Core DFIR Tools (15 tools)
| Category | Tool | Description |
|---|---|---|
| Clients | list_clients |
Search and list Velociraptor endpoints |
get_client_info |
Get detailed information about a client | |
label_client |
Add/remove labels from clients | |
quarantine_client |
Quarantine or release endpoints | |
| Artifacts | list_artifacts |
List available Velociraptor artifacts |
get_artifact |
Get full artifact definition | |
collect_artifact |
Schedule artifact collection on a client | |
| Hunts | create_hunt |
Create a mass collection campaign |
list_hunts |
List existing hunts | |
get_hunt_results |
Retrieve results from a hunt | |
modify_hunt |
Start, pause, stop, or archive hunts | |
| Flows | list_flows |
List collection flows for a client |
get_flow_results |
Get results from a collection | |
get_flow_status |
Check collection status | |
cancel_flow |
Cancel a running collection | |
| VQL | run_vql |
Execute arbitrary VQL queries |
vql_help |
Get help on VQL syntax and plugins |
Deployment Tools (18 tools)
| Category | Tool | Description |
|---|---|---|
| Server Deployment | deploy_server_binary |
Deploy Velociraptor server as standalone binary |
deploy_server_docker |
Deploy Velociraptor server using Docker | |
deploy_server_cloud |
Deploy Velociraptor server to AWS/Azure cloud | |
generate_server_config |
Generate server configuration with certificates | |
| Agent Deployment | deploy_agent_gpo |
Generate GPO deployment package for Windows |
deploy_agent_winrm |
Deploy agents via WinRM to Windows endpoints | |
deploy_agent_ssh |
Deploy agents via SSH to Linux/macOS endpoints | |
deploy_agent_ansible |
Generate Ansible playbook for agent deployment | |
build_offline_collector |
Build standalone offline collector | |
generate_client_config |
Generate client configuration file | |
| Deployment Management | list_deployments |
List tracked deployment operations |
get_deployment_status |
Get detailed status of a deployment | |
verify_deployment |
Verify deployment health and connectivity | |
rollback_deployment |
Rollback a failed deployment | |
| Credentials | store_credential |
Securely store deployment credentials |
list_credentials |
List stored credential aliases | |
delete_credential |
Remove stored credentials | |
| Utilities | download_velociraptor |
Download Velociraptor binary for platform |
MCP Resources
Browse Velociraptor data through standardized URIs:
velociraptor://clients- Browse connected endpointsvelociraptor://clients/{client_id}- View specific client detailsvelociraptor://hunts- Browse hunt campaignsvelociraptor://hunts/{hunt_id}- View specific hunt detailsvelociraptor://artifacts- Browse available artifactsvelociraptor://server-info- View server informationvelociraptor://deployments- Browse deployment operations and status
MCP Prompts (8 prompts)
Pre-built DFIR and deployment workflow prompts:
| Prompt | Category | Description |
|---|---|---|
investigate_endpoint |
DFIR | Comprehensive endpoint investigation workflow |
threat_hunt |
DFIR | Create and execute threat hunting campaigns |
triage_incident |
DFIR | Rapid incident triage and scoping |
malware_analysis |
DFIR | Analyze suspicious files or processes |
lateral_movement |
DFIR | Detect lateral movement indicators |
deploy_velociraptor |
Deployment | Interactive Velociraptor deployment wizard |
scale_deployment |
Deployment | Plan enterprise-scale agent rollout |
troubleshoot_deployment |
Deployment | Diagnose and fix deployment issues |
Installation
Prerequisites
- Python 3.10 or higher
- A running Velociraptor server with API access enabled
- API client credentials (see Configuration)
Install from source
git clone https://github.com/yourusername/megaraptor-mcp.git
cd megaraptor-mcp
# Core DFIR func
Tools (21)
list_clientsSearch and list Velociraptor endpointsget_client_infoGet detailed information about a clientlabel_clientAdd/remove labels from clientsquarantine_clientQuarantine or release endpointslist_artifactsList available Velociraptor artifactsget_artifactGet full artifact definitioncollect_artifactSchedule artifact collection on a clientcreate_huntCreate a mass collection campaignlist_huntsList existing huntsget_hunt_resultsRetrieve results from a huntmodify_huntStart, pause, stop, or archive huntslist_flowsList collection flows for a clientget_flow_resultsGet results from a collectionget_flow_statusCheck collection statuscancel_flowCancel a running collectionrun_vqlExecute arbitrary VQL queriesvql_helpGet help on VQL syntax and pluginsdeploy_server_binaryDeploy Velociraptor server as standalone binarydeploy_server_dockerDeploy Velociraptor server using Dockerdeploy_agent_sshDeploy agents via SSH to Linux/macOS endpointsverify_deploymentVerify deployment health and connectivityEnvironment Variables
VELOCIRAPTOR_API_CONFIGrequiredPath to the Velociraptor API client configuration fileConfiguration
{
"mcpServers": {
"megaraptor": {
"command": "python",
"args": ["-m", "megaraptor_mcp"],
"env": {
"VELOCIRAPTOR_API_CONFIG": "/path/to/api.config.yaml"
}
}
}
}