Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Connects AI agents with CrowdStrike Falcon for security analysis and automation.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
FALCON_CLIENT_ID, FALCON_CLIENT_SECRET, FALCON_BASE_URL, FALCON_MEMBER_CID, FALCON_MCP_MODULES, FALCON_MCP_TRANSPORT, FALCON_MCP_DEBUG, FALCON_MCP_HOST, FALCON_MCP_PORT, FALCON_MCP_USER_AGENT_COMMENT, FALCON_MCP_STATELESS_HTTP, FALCON_MCP_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"falcon": {
"command": "uvx",
"args": [
"falcon-mcp"
],
"env": {
"FALCON_CLIENT_ID": "your-value",
"FALCON_CLIENT_SECRET": "your-value",
"FALCON_BASE_URL": "your-value",
"FALCON_MEMBER_CID": "your-value",
"FALCON_MCP_MODULES": "your-value",
"FALCON_MCP_TRANSPORT": "your-value",
"FALCON_MCP_DEBUG": "your-value",
"FALCON_MCP_HOST": "your-value",
"FALCON_MCP_PORT": "your-value",
"FALCON_MCP_USER_AGENT_COMMENT": "your-value",
"FALCON_MCP_STATELESS_HTTP": "your-value",
"FALCON_MCP_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add falcon --env FALCON_CLIENT_ID=your-value --env FALCON_CLIENT_SECRET=your-value --env FALCON_BASE_URL=your-value --env FALCON_MEMBER_CID=your-value --env FALCON_MCP_MODULES=your-value --env FALCON_MCP_TRANSPORT=your-value --env FALCON_MCP_DEBUG=your-value --env FALCON_MCP_HOST=your-value --env FALCON_MCP_PORT=your-value --env FALCON_MCP_USER_AGENT_COMMENT=your-value --env FALCON_MCP_STATELESS_HTTP=your-value --env FALCON_MCP_API_KEY=your-value -- uvx falcon-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"falcon": {
"command": "uvx",
"args": [
"falcon-mcp"
],
"env": {
"FALCON_CLIENT_ID": "your-value",
"FALCON_CLIENT_SECRET": "your-value",
"FALCON_BASE_URL": "your-value",
"FALCON_MEMBER_CID": "your-value",
"FALCON_MCP_MODULES": "your-value",
"FALCON_MCP_TRANSPORT": "your-value",
"FALCON_MCP_DEBUG": "your-value",
"FALCON_MCP_HOST": "your-value",
"FALCON_MCP_PORT": "your-value",
"FALCON_MCP_USER_AGENT_COMMENT": "your-value",
"FALCON_MCP_STATELESS_HTTP": "your-value",
"FALCON_MCP_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"falcon": {
"type": "stdio",
"command": "uvx",
"args": [
"falcon-mcp"
],
"env": {
"FALCON_CLIENT_ID": "your-value",
"FALCON_CLIENT_SECRET": "your-value",
"FALCON_BASE_URL": "your-value",
"FALCON_MEMBER_CID": "your-value",
"FALCON_MCP_MODULES": "your-value",
"FALCON_MCP_TRANSPORT": "your-value",
"FALCON_MCP_DEBUG": "your-value",
"FALCON_MCP_HOST": "your-value",
"FALCON_MCP_PORT": "your-value",
"FALCON_MCP_USER_AGENT_COMMENT": "your-value",
"FALCON_MCP_STATELESS_HTTP": "your-value",
"FALCON_MCP_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
FALCON_BASE_URL envFALCON_MEMBER_CID envFALCON_MCP_MODULES envFALCON_MCP_TRANSPORT envFALCON_MCP_DEBUG envFALCON_MCP_HOST envFALCON_MCP_PORT envFALCON_MCP_USER_AGENT_COMMENT envFALCON_MCP_STATELESS_HTTP env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 CrowdStrike 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:FALCON_CLIENT_ID, FALCON_CLIENT_SECRET, FALCON_MCP_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.20.2)于3天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, FactLot
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Cited CRE facts and deterministic calculators for agents: rent, CAM, debt sizing, IRR, parcel IDs.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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]
falcon-mcp is now in maintenance mode. Development continues in CrowdStrike MCP, CrowdStrike's hosted MCP server, and we recommend moving to it. falcon-mcp stays supported and will keep getting security fixes, but new features will only ship in CrowdStrike MCP. See Moving to CrowdStrike MCP for what this means for you.
Full docs are available at [developer.crowdstrike.com/falcon-mcp](https://developer.crowdstrike.com/falcon-mcp/).
falcon-mcp started as an open source project to work out how AI agents should use Falcon. A lot of what we built here, including fixes and ideas from your issues and pull requests, carries forward into CrowdStrike MCP. CrowdStrike MCP is a CrowdStrike product rather than an open source project, so new development won't happen in this repository. Thanks to everyone who filed issues and sent pull requests.
For most teams, CrowdStrike MCP is the better choice now:
falcon_* names, so prompts and agent instructions written for falcon-mcp carry over.What happens to falcon-mcp:
| Module | Description |
|---|---|
| Core | Basic connectivity and system information |
| AgentWorks | Call, list, and observe Charlotte AI agents and their execution traces |
| Case Management | Case lifecycle management, evidence attachment, tagging, and templates |
| Cloud Security | Kubernetes containers, image vulnerabilities, CSPM asset inventory, IOM findings, suppression rules, cloud risks, cloud insights, and cloud groups |
| Correlation Rules | Search, create, update, and manage NG-SIEM correlation rules |
| Custom IOA | Create and manage Custom IOA behavioral detection rules and rule groups |
| Data Security | Search, create, and update Data Security classifications, policies, content patterns, applications, web locations, sensitivity labels, and file types |
| Detections | Find, aggregate, and analyze detections to understand malicious activity |
| Discover | Search application inventory and managed/unmanaged assets, including drive encryption and system-insights posture |
| Exclusions | Search, create, update, and delete IOA, machine learning, sensor visibility, and certificate-based exclusions |
| Firewall Management | Search and manage firewall rules and rule groups |
| Fusion SOAR | Search Fusion SOAR workflow definitions and executions, read execution results, and run on-demand workflows |
| Guardian | Monitor AI agent activity, sessions, tool usage, and inventory |
| Host Groups | Search, create, update, and delete host groups; manage group membership |
| Hosts | Manage and query host/device information |
| Identity Protection | Entity investigation and identity protection analysis |
| Intel | Research threat actors, IOCs, and intelligence reports |
| IOC | Search, create, and remove custom indicators of compromise |
| NGSIEM | Execute CQL queries against Next-Gen SIEM |
| Policies | Search, create, update, and delete prevention, sensor update, firewall, device control, response, and content update policies; manage host-group assignment, enable/disable, and precedence |
| Quarantine | Search quarantine records, preview action counts, and release, unrelease, or delete quarantined files |
| Real Time Response | Audit, summarize, and run read-only RTR triage workflows |
| Recon | Search and aggregate Falcon Intelligence Recon notifications (recon alerts), monitoring rules, and exposed-data records for dark web, leaked credentials, and typosquatting, and preview prospective rule noise |
| Scheduled Reports | Manage scheduled reports and download report files |
| Sensor Usage | Access and analyze sensor usage data |
| Serverless | Search for vulnerabilities in serverless functions |
| Shield | SaaS security posture, checks, alerts, and app inventory |
| Spotlight | Manage and analyze vulnerability data and security assessments |
| Zero Trust Assessment | Retrieve Zero Trust Assessment posture scores and sensor and OS hardening signals for hosts |
See the Module Overview for required API scopes, available tools, and FQL resources.
[!NOTE]
The Guardian module reads the
/aidrAPI, whose route and parameter surface is not
yet uniform across Falcon deployments. Some tools return HTTP 400 or 404 where an
older surface is live. See the Guardian module docs for the details.
uv tool install falcon-mcp
pip install falcon-mcp
Set the required environment variables (or use a .env file — see the Configuration Guide):
export FALCON_CLIENT_ID="your-client-id"
export FALCON_CLIENT_SECRET="your-client-secret" export FALCON_BASE_URL="https://api.crowdstrike.com"
falcon-mcp
See the Getting Started guide for full installation and configuration details.
uvx (recommended){
"mcpServers": { "falcon-mcp": { "command": "uvx", "args": [ "--env-file", "/path/to/.env", "falcon-mcp" ] } } }
{
"mcpServers": { "falcon-mcp": { "command": "uvx", "args": [ "--env-file", "/path/to/.env", "falcon-mcp", "--modules", "detections,hosts,intel" ] } } }
{
"mcpServers": { "falcon-mcp-docker": { "command": "docker", "args": [ "run", "-i", "--rm", "--env-file", "/full/path/to/.env", "quay.io/crowdstrike/falcon-mcp:latest" ] } } }
See the Usage guide for all command line options, module configuration, and library usage.
# Pull the latest image
docker pull quay.io/crowdstrike/falcon-mcp:latest
docker run -i --rm --env-file /path/to/.env quay.io/crowdstrike/falcon-mcp:latest
docker run --rm -p 8000:8000 --env-file /path/to/.env \ quay.io/crowdstrike/falcon-mcp:latest \ --transport streamable-http --host 0.0.0.0 --api-key your-secret-key
[!CAUTION]
HTTP transports have no authentication by default. Binding to a non-loopback address (
--host 0.0.0.0)
exposes an unauthenticated server that anyone who can reach the port can drive with your CrowdStrike
credentials. Keep the default loopback bind for local use and set
--api-keywhenever you bind wider.
Managed runtimes such as AWS Bedrock AgentCore and Google Cloud Run sit behind their own network
security layer, so this does not apply to them. See the
See the Docker Deployment guide for building locally, custom ports, and advanced configurations.
Running many modules at once inflates the context window every AI client must hold. Dynamic mode replaces the full tool surf
只显示了开头部分;其余内容请在仓库中阅读