Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Descripción del creador (original en inglés)
Community extension of CrowdStrike falcon-mcp with near-complete Falcon API coverage
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"falcon": {
"command": "uvx",
"args": [
"falcon-mcp-extended"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add falcon -- uvx falcon-mcp-extendedPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"falcon": {
"command": "uvx",
"args": [
"falcon-mcp-extended"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"falcon": {
"type": "stdio",
"command": "uvx",
"args": [
"falcon-mcp-extended"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 8 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub rijul170, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (0.9.0) llegó al registro hace 4 meses.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Python (uv) en tu computadora.
En la misma categoría: Spec Driven Development, Remote Desktop Commander, NexusWindows
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
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.
Windows computer use in the background: desktop apps driven without your mouse or keyboard.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
[!NOTE]
This is a community extension of CrowdStrike's official [falcon-mcp](https://github.com/CrowdStrike/falcon-mcp) server (MIT licensed). It adds 106 auto-generated API wrapper modules (~904 additional tools) on top of the official curated tool set, for near-complete CrowdStrike Falcon API coverage. This project is not affiliated with, maintained by, or endorsed by CrowdStrike. If you only need the curated SOC workflows, use the official server; use this project when you need API surface the official server doesn't expose yet.
For SOC analysts and security engineers: Stop tab-switching between CrowdStrike, your ticketing system, and your notes. Ask Claude to triage the alert, pull the process tree, check if the hash ran on other hosts, and draft the IR note — all in one conversation.
falcon-mcp-extended is a Model Context Protocol (MCP) server that gives AI agents — including Claude — direct, structured access to the CrowdStrike Falcon platform for intelligent security operations.
This server bridges AI assistants and the CrowdStrike Falcon platform, enabling SOC analysts to ask natural-language questions and get answers backed by live Falcon data. It exposes Falcon's detection, investigation, response, and intelligence capabilities as MCP tools, so an AI agent can search detections, pivot through behaviors, contain hosts, and query threat intelligence — all from a single conversation. Designed for both interactive SOC workflows and automated security pipelines, it supports MSSP Flight Control so multi-tenant environments can be queried without switching consoles.
| Layer | Module count | Approximate tool count | Enabled by default |
|---|---|---|---|
| Curated modules (from upstream, plus additions) | 50 | ~392 | Yes |
Auto-generated API wrappers (gen_*) — this project's addition | 106 | ~904 additional | No (opt-in) |
The default mode exposes the curated layer (~392 tools), which covers every major SOC workflow with well-described, ergonomic tools. The full generated layer (total ~1,296 tools) can be enabled with FALCON_MCP_ENABLE_GENERATED=1 for complete API surface coverage — including Message Center, ODS scans, response/content/device-control policies, installation tokens, MalQuery, FalconX Sandbox, QuickScan Pro, sample uploads, FileVantage, Falcon Complete Dashboard, cloud registration (AWS/Azure/GCP/OCI), Kubernetes admission control, container images/alerts/detections, network scanning, NGSIEM administration, knowledge bases, and much more.
member_cid to scope any query to a specific managed tenantuv (recommended) or pip[!IMPORTANT]
The correct package name is `falcon-mcp-extended`. Do not
pip install falcon-mcp— that is CrowdStrike's official package, which does not include the extended module layer.
pip install falcon-mcp-extended
Or with uv:
uv pip install falcon-mcp-extended
git clone https://github.com/rijul170/falcon-mcp.git
cd falcon-mcp uv sync --all-extras uv run falcon-mcp
uvx --from git+https://github.com/rijul170/falcon-mcp falcon-mcp
pip install git+https://github.com/rijul170/falcon-mcp
All configuration is driven by environment variables (or a .env file in the working directory). CLI flags mirror every env var and take precedence when both are set.
| Variable | Required | Description | Example |
|---|---|---|---|
FALCON_CLIENT_ID | Required | CrowdStrike API Client ID | abc123def456 |
FALCON_CLIENT_SECRET | Required | CrowdStrike API Client Secret | your-client-secret |
FALCON_BASE_URL | Required | API endpoint URL for your region | https://api.crowdstrike.com |
FALCON_MEMBER_CID | Optional | Default child CID for MSSP Flight Control; targets all queries at that tenant | ABC123DEF456GHI789 |
FALCON_MCP_TRANSPORT | Optional | Transport protocol: stdio, sse, or streamable-http (default: stdio) | streamable-http |
FALCON_MCP_HOST | Optional | Bind host for HTTP transports (default: 127.0.0.1) | 0.0.0.0 |
FALCON_MCP_PORT | Optional | Bind port for HTTP transports (default: 8000) | 8000 |
FALCON_MCP_MODULES | Optional | Comma-separated list of modules to enable; omit to enable all | detections,incidents,intel |
FALCON_MCP_ENABLE_GENERATED | Optional | Set to 1 to load all 106 auto-generated modules (~1,296 tools total) | 1 |
FALCON_MCP_READONLY | Optional | Set to true to suppress all mutating tools at startup | true |
FALCON_MCP_ALLOW_DESTRUCTIVE | Optional | Set to true to enable all destructive tools, or a comma-separated list of specific tool names to allow selectively | falcon_perform_host_action,falcon_execute_rtr_active_responder_command |
FALCON_MCP_API_KEY | Optional | API key for x-api-key header authentication on HTTP transports | your-api-key |
FALCON_MCP_STATELESS_HTTP | Optional | Set to true to enable stateless HTTP mode for horizontally-scaled deployments | true |
FALCON_MCP_DEBUG | Optional | Set to true to enable verbose debug logging | true |
Region base URLs:
| Region | Base URL |
|---|---|
| US-1 | https://api.crowdstrike.com |
| US-2 | https://api.us-2.crowdstrike.com |
| EU-1 | https://api.eu-1.crowdstrike.com |
| GOV-1 | https://api.laggar.gcw.crowdstrike.com |
HTTP mode (streamable-http) is recommended for Claude Code and other AI development environments that support persistent server connections.
Step 1 — Start the server:
FALCON_CLIENT_ID=your-client-id \
FALCON_CLIENT_SECRET=your-client-secret \ FALCON_BASE_URL=https://api.crowdstrike.com \ FALCON_MCP_TRANSPORT=streamable-http \ uv run falcon-mcp
Step 2 — Add to `.claude/settings.json` (project) or `~/.claude/settings.json` (global):
{
"mcpServers": { "falcon-mcp": { "type": "http", "url": "http://localhost:8000/mcp" } } }
For API key-protected deployments, add the header:
{
"mcpServers": { "falcon-mcp": { "type": "http", "url": "http://localhost:8000/mcp", "headers": { "x-api-key": "your-api-key" } } } }
Stdio mode works best for Claude Desktop. Credentials are passed directly in the MCP server configuration.
{
"mcpServers": { "falcon-mcp": { "command": "uvx", "args": ["--from", "git+https://github.com/rijul170/falcon-mcp", "falcon-mcp"], "env": { "FALCON_CLIENT_ID": "your-client-id", "FALCON_CLIENT_SECRET": "your-client-secret", "FALCON_BASE_URL": "https://api.crowdstrike.com" } } } }
To load credentials from a .env file instead of embedding them in the config:
{
"mcpServers": { "falcon-mcp": { "command": "uvx", "args": ["--env-file", "/path/to/.env", "--from", "git+https://github.com/rijul170/falcon-mcp", "falcon-mcp"] } } }
Build the image locally from the included Dockerfile:
git clone https://github.com/rijul170/falcon-mcp.git
cd falcon-mcp docker build -t falcon-mcp-extended .
docker run -i --rm --env-file /path/to/.env falcon-mcp-extended
docker run --rm -p 8000:8000 --env-file /path/to/.env \ falcon-mcp-extended --transport streamable-http --host 0.0.0.0
The server has first-class support for CrowdStrike Flight Control environments.
Default tenant targeting: Set FALCON_MEMBER_CID to route all queries to a specific child CID without changing anything else:
export FALCON_MEMBER_CID="CHILD_CID_HERE"
Per-request tenant targeting: Every tool that accepts a member_cid parameter can override the default at call time. This lets an AI agent query multiple child tenants in a single session without restarting the server:
"Search for critical detections in tenant ABC123 and compare with tenant XYZ789."
Flight Control module: The flight_control module provides tools to enumerate all child accounts, list CID groups and user groups, query MSSP role assignments, and manage group membership.
MSSP API scopes: The parent CID must have Flight Control API scopes enabled. Child CID API keys are not required when querying through the parent.
| Module | Key Capabilities |
|---|---|
alerts | Search and manage unified alerts across all Falcon alert types |
| detections | Find and
Solo se muestra el principio; lee el resto en el repo