security MCP Server
Local stdio MCP server for Bitwarden (Public API + Secrets Manager). 50+ admin tools for members, groups, collections, policies, licensing, projects, and secrets. For Claude Desktop / Claude Code.
Discovered via github-topic:model-context-protocol and last synced 3mo ago.
1. Install the package
npx the-real-bitwarden-mcp
2. Add to claude_desktop_config.json
{
"mcpServers": {
"the-real-bitwarden-mcp": {
"command": "npx",
"args": [
"the-real-bitwarden-mcp"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
self-host mode
present
Defaults to last 24 h when `start`/`end` are omitted
cloud mode
Version prefix
available
cloud mode
cloud mode
Value
SM tools
Default fields
self-host mode
SM project/secret create/list
`id`, `name`, `externalId`
self-host mode
cloud mode
On unsupported platforms the MCP still starts and all Public-API tools work normally. The `bws_project_*` and `bws_secret_*` tools return "Secrets Manager SDK not available on this platform" at call time. If Bitwarden ships SDK binaries for a new platform, simply `npm install` will pick them up — no MCP code change needed. ## Setup ```bash git clone <repo-url> cd <repo> npm install # also pulls the platform-specific SDK binary automatically cp .env.example .env # Fill in .env — see "Configuration". npm run refresh-spec # pull Swagger from your self-host (optional) npm run generate # build the generated tool list (optional) npm run build ``` The SDK binary is an optional dependency — `npm install` succeeds even on unsupported platforms (the binary simply won't be present, and SM tools will return a clear "not available" message). ## Configuration All values are read from `.env`. **At least one instance must be fully configured**, otherwise the server refuses to start.
self-host mode
SM tools (optional)
`id`, `externalId`
SM tools (optional)
`id`, `email`, `name`, `type`, `status`, `twoFactorEnabled`
absent
真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。
Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators
Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS
Implements eBPF-based security monitoring using Cilium Tetragon for real-time process execution tracking, network connection observability, file access auditing, and runtime enforcement. Covers TracingPolicy CRD authoring with kprobe/tracepoint hooks, in-kernel filtering via matchArgs/matchBinaries selectors, JSON event export, and integration with SIEM pipelines. Use when building kernel-level runtime security observability for Linux hosts or Kubernetes clusters.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Learn how to use the absolute-audit Claude skill. Complete guide with installation instructions and examples.
Learn how to use the token-scam-analysis Claude skill. Complete guide with installation instructions and examples.
Learn how to use the absolute-upgrade Claude skill. Complete guide with installation instructions and examples.