FalconCAUTION
Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://badge.fury.io/py/falcon-mcp) [](https://pypi.org/project/falcon-mcp/) [](https://opensource.org/licenses/MIT) [](https://registry.modelcontextprotocol.io/?q=io.github.CrowdStrike%2Ffalcon-mcp&all=1) [](https://github.com/mcp/CrowdStrike/falcon-mcp) [](https://geminicli.com/extensions/?name=CrowdStrikefalcon-mcp)
falcon-mcp is a Model Context Protocol (MCP) server that connects AI agents with the CrowdStrike Falcon platform, powering intelligent security analysis in your agentic workflows. It delivers programmatic access to essential security capabilities—including detections, threat intelligence, and host management—establishing the foundation for advanced security operations and automation.
[!IMPORTANT] Pre-1.0 release: falcon-mcp is under active development ahead of 1.0. Tool names, parameters, and response shapes can still change between minor releases, so pin a version and check the changelog before upgrading. The project is actively maintained by CrowdStrike and supported through GitHub Issues; CrowdStrike customers can also raise questions through their usual Technical Support channels. See [SUP
40c2b5c5e88eOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add falcon-mcp --env FALCON_CLIENT_ID=${FALCON_CLIENT_ID} --env FALCON_CLIENT_SECRET=${FALCON_CLIENT_SECRET} --env FALCON_MCP_API_KEY=${FALCON_MCP_API_KEY} -- uvx falcon-mcp==0.19.0Trust audit
CAUTIONgrade C · trust 80/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (21)
submodule = importlib.import_module(import_path)
submod = importlib.import_module(f"falcon_mcp.modules.{name}.{subname}")mod = importlib.import_module(f"falcon_mcp.modules.{name}").env.dev.example
.markdownlint.json
return getattr(importlib.import_module(root_module), class_name)
"a/../../oauth2/token",
repository="a/../../oauth2/token",
# Run with SSE transport — listens at http://127.0.0.1:8000/sse
# Run — listens at http://0.0.0.0:8080/mcp
"url": "http://127.0.0.1:8000/sse"
"url": "http://127.0.0.1:8000/mcp"
# Server listens at http://127.0.0.1:8000/sse
falcon-mcp
If running the server on a remote host or in Docker, send the API key you configured with `--api-key`
- `load_config`: Load configuration from environment variables and arguments
# Load environment variables from .env file
- "Open a high-severity case for the credential theft alerts and attach them as evidence"
access level, password protection status, and last access/modification timestamps.
> If `falcon-mcp` isn't found after installation, update your shell `PATH`.
Gates applied: no_behavioural_pass.
40c2b5c5e88efull audit observations/trust-audit/mcp-server/crowdstrike__falcon.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 40c2b5c5e88e | CAUTION | C | 80 | first audit |
Questions
What is the Falcon MCP server?
Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting
Is Falcon safe to connect to an agent?
With care. The audit graded it C (80/100) and found 21 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Falcon need?
It reads FALCON_CLIENT_ID, FALCON_CLIENT_SECRET and FALCON_MCP_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Falcon run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as falcon-mcp.
How current is this page?
The grade is for one exact copy of the source (40c2b5c5e88e), read on 2026-10-06. The repository is watched and re-audited when it changes.