security MCP Server
Persistent SSH PTY session manager for MCP clients with actor-aware input tracking, split dashboard rendering, and automatic session cleanup. | https://zw-awa.github.io/ssh-session-mcp/
Discovered via github-topic:claude-mcp and last synced 3mo ago.
1. Install the package
npx ssh-session-mcp
2. Add to claude_desktop_config.json
{
"mcpServers": {
"ssh-session-mcp": {
"command": "npx",
"args": [
"ssh-session-mcp"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
Read line-numbered mixed terminal history
Resize the PTY
Legacy single-target SSH mode
List tracked viewer processes
Meaning
Send control keys such as `ctrl_c`, arrows, or `tab`
Suggested next step
List tracked sessions
Enable sentinel completion markers
One-step connect flow for agents
Behavior
Open a session with explicit SSH parameters
Read buffered terminal output by offset
Open or reuse the local viewer
Normalized outcome: `success`, `partial_success`, `blocked`, `failure`
Normalized failure type when blocked or failed
Local JSONL log directory
Runtime safety mode
Short supporting facts
Short human/agent readable summary
Relaxes the guardrails for advanced use, while still blocking a small set of clearly destructive abuse cases.
Container image build definition
Only the agent can type. User input is blocked until the policy changes.
Add or update a session-specific custom policy rule
Long-poll for output and dashboard changes
Runtime overview
Profile-based mode or config outside cwd
User and agent can both type into the shared terminal.
Async poller
Send raw PTY input
Inspect lock state, warnings, running command state, and viewer health
Close a session cleanly
What the operator experiences
Legacy single-target SSH mode
Viewer enabled
Auto-open viewer tab
Purpose
Default. Automatically blocks obviously dangerous, interactive, or never-ending commands.
Restore inherited rules for the current session
Choose the default session
Required When
Custom viewer bind
Docker Compose image override
Purpose
Remove a session-specific custom policy rule
Multi-agent / multi-client isolation
Runtime metadata logging
Only the user can type. Agent write actions are blocked.
Retry executor
List configured devices and defaults
Legacy single-target SSH mode
Local demo mode
The user can start typing without fighting the agent. While the user is actively drafting input, agent writes are blocked.
Show inherited policy defaults and the current session rule set
Main command execution tool
Password-based auth
Browser debug controls
Key-based auth in legacy mode
Docker Compose profile-based example
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.