What is the current status of falcon-mcp?
It is in **public preview** under active development. Features may change before the stable 1.0 release, so production deployments are not recommended.
Crowdstrike Falcon MCP Server
@CrowdStrike
Basic information
About Crowdstrike Falcon MCP Server
Connects AI agents with the CrowdStrike Falcon platform for intelligent security analysis, providing programmatic access to detections, incidents, behaviors, threat intelligence, hosts, vulnerabilities, and identity protection capabilities.
Crowdstrike Falcon MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"falcon-mcp": {
"command": "uvx",
"args": [
"falcon-mcp"
],
"env": {
"FALCON_CLIENT_ID": "your-client-id",
"FALCON_CLIENT_SECRET": "your-client-secret",
"FALCON_BASE_URL": "https://api.crowdstrike.com"
}
}
}
}Crowdstrike Falcon MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Crowdstrike Falcon?
Crowdstrike Falcon is a Model Context Protocol (MCP) server that connects AI agents with the CrowdStrike Falcon platform for security analysis. It provides programmatic access to detections, incidents, behaviors, threat intelligence, and other security capabilities.
How to use Crowdstrike Falcon?
Install the server with pip install falcon-mcp (requires Python 3.11+). Configure CrowdStrike API credentials via environment variables (FALCON_CLIENT_ID, FALCON_CLIENT_SECRET), then run falcon-mcp on the command line or integrate with an MCP client like Claude Desktop. Modules can be enabled or disabled using command-line flags.
Key features of Crowdstrike Falcon
- Detection search and analysis
- Incident investigation and CrowdScore monitoring
- Threat actor and IOC intelligence research
- Host/device inventory and management
- Vulnerability search and management
- Identity protection entity investigation
Use cases of Crowdstrike Falcon
- Threat hunting: Search detections to uncover malicious activity.
- Incident response: Analyze incidents, behaviors, and CrowdScore.
- Threat intelligence: Research adversaries, indicators, and reports.
- Asset management: Query host inventory and device details.
- Vulnerability management: Search and assess vulnerabilities.
Frequently asked questions
What API scopes are required?
Scopes depend on the modules you enable. For example, Detections needs `Alerts:read`, Incidents needs `Incidents:read`, and Intel needs multiple Falcon Intelligence scopes. See the README for the full list.
Can I trust AI-generated FQL queries?
FQL has nuanced syntax. AI-generated filters should be tested and validated before production use. Start with simple queries and gradually build complexity.
How do I install and configure falcon-mcp?
Install via `pip install falcon-mcp` with Python 3.11+. Copy `.env.example` to `.env` and set `FALCON_CLIENT_ID` and `FALCON_CLIENT_SECRET` from your CrowdStrike API credentials.
More Other MCP servers
MaxKB
1Panel-dev🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
22.0K
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
15.9K
Senso MCP for Joomla
sensomediaSenso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
16.7K
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Comments