Install CrowdStrike Falcon in Claude Code
claude mcp add crowdstrike-falcon -e FALCON_CLIENT_ID=... -e FALCON_CLIENT_SECRET=... -- uvx falcon-mcp{
"mcpServers": {
"crowdstrike-falcon": {
"command": "uvx",
"args": [
"falcon-mcp"
],
"env": {
"FALCON_CLIENT_ID": "...",
"FALCON_CLIENT_SECRET": "..."
}
}
}
}Replace each ... with your own value.
Frequently asked questions
What does the CrowdStrike Falcon MCP server do?
Connects AI agents with CrowdStrike Falcon for security analysis and automation.
Is the CrowdStrike Falcon MCP server free?
The server is free, but you will likely need an account. The server itself is free, but it connects to a service that needs an account or API key, which may have paid tiers. Check the provider for current pricing.
Does CrowdStrike Falcon run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add CrowdStrike Falcon to Claude Code?
Run: claude mcp add crowdstrike-falcon -e FALCON_CLIENT_ID=... -e FALCON_CLIENT_SECRET=... -- uvx falcon-mcp
More security & identity MCP servers
View allOpenWorkProof
dengyier/OpenWorkProof
Verifiable execution protocol for agent tool calls: signed policy decisions, causal evidence chains and offline verification from a SQLite ledger.
Vibe Prospecting
explorium-ai/vibeprospecting-mcp
B2B company and contact data for lead lists, enrichment, research, and outreach. OAuth sign-in.
EchelonGraph CVE & Exposure
echelongraph/echelongraph-mcp
Keyless, read-only CVE and internet-exposure intelligence: CVE lookup and search, CISA KEV, EPSS history, CWE, vendor advisories (MSRC, Red Hat, Cisco, GHSA and more), SBOM and manifest checks, and aggregate exposure radars. Use the hosted endpoint (mcp.echelongraph.io) with no install, or run locally with npx.
squirrelscan
squirrelscan/squirrelscan
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
Wazuh
gbrigandi/mcp-server-wazuh
Access real-time security alerts and event data from Wazuh SIEM.
DashClaw
ucsandman/DashClaw
Fail-closed approval layer for unattended agent runs: checks actions against org policy, requests human approval and logs every decision to a causal ledger.