Explore

Command line interface for MCP clients with secure execution and customizable security policies

in the readmeMCP server enables secure command-line execution with robust security measures including command whitelisting, path validation, and execution controls. Perfect for providing controlled CLI access

Python·MIT·★ 177·No key

A general-purpose server-ops MCP server — logs, resources, code edit, Nginx/certs via AI. Local + SSH modes with confirmations & secret redaction. 中文文档见 README.zh-CN.md

in the readmeSupports **local** and **remote (SSH)** modes, with built-in two-step confirmation, command whitelisting, path-traversal protection, and automatic secret redaction. ## Features - 🔍 **Log troubleshooting**: list / read

Node.js·MIT·Few stars·No key

SSH MCP server: execute commands, transfer files, and forward ports on remote servers via MCP.

in the readmeagent a small, auditable set of tools, each gated by an optional command whitelist/blacklist and path restrictions, so the operator controls exactly what the agent can

Go·MIT·★ 32·No key

DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.

in the skill textfor inter-Agent communication. - **Security Check**: All file and command operations are validated against a path whitelist. - **Multi-Agent Collaboration**: Agents in different Tabs can message

Skill·MIT·★ 2.4k·No key

High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox, automate transfers, a

in the readmedownload`, `upload`), recipes, and Mermaid architectural diagrams. | ** Command Reference ** | | 🛡️ **Security Sandbox Guide** | Explains the memory-based wrapper injection, whitelist configuration schemas (`sandbox_config.json`), and security validation scenarios

Go·MIT·★ 173·No key

MCP server for secure SSH remote management — 337 tools across 74 groups for DevOps, Docker, Kubernetes, databases, systemd, Windows, cloud, compliance & more. Built in Rust.

in the readmePowerShell Remoting), Telnet, K8s Exec, Serial, AWS SSM, Azure, GCP - **Security-first** — command whitelist/blacklist, 63 secret-redaction patterns + entropy detection, tamper-proof session recording, MCP confirmation

Skill·MIT·★ 10·No key

Zero-dependency Web Application Firewall in Go. Single binary. Three deployment modes. Tokenizer-based detection.

in the readmerequired. --- ## Features **Detection & Protection** - Eleven attack detectors: SQL injection, XSS, path traversal, command injection, XXE, SSRF, SSTI, NoSQL injection, HTTP request smuggling, open redirect, GraphQL depth/complexity

Go·MIT·★ 34·No key

in the readmePath check** — every path, glob match and redirect target in every command must be whitelisted or session-approved 5. **Approval check** — write/system commands require approval Pipes

Python·MIT·★ 10·No key

Bitbond Token Tool MCP - deploy and manage compliant ERC20 tokens from any AI agent (OpenClaw, Claude Code, Cursor, Windsurf)

in the readmeDeploy a token called Green Bond A, 1M supply on Base, with whitelist and pausable." ``` → CertiK-audited ERC-20 deployed on-chain in ~30 seconds. Contract

Node.js·MIT·★ 6·Needs a key

A powerful Model Context Protocol (MCP) server offering a broad set of practical tools across multiple categories — built with FastMCP.一款强大的模型上下文协议（MCP）服务器，提供覆盖多个类别的丰富实用工具——基于 FastMCP 构建。

in the readmeTOML parsing and manipulation - **⚡ Command Execution** (5 tools): Secure allowlist-based command execution: run whitelisted commands with argument sanitization, timeout protection, output size limits and audit

Python·MIT·★ 4·Few stars·No key

Atlas is the company facts your AI agents can trust: every one carries its source, its date, and the name of the person who approved it. Open source, runs in your VPC.

in the readmeNovaMart's orders. (Claude Code, VS Code and other clients: the same command with `--client generic` prints a block to paste. On WSL2, write `bun

Node.js·AGPL-3.0·★ 1·Few stars·No key

An MCP server that exposes package.json scripts as tools for agents.

in the readmehardcoded paths). - 📦 **Works with everything**: npm, pnpm, yarn, and bun. - 🔒 **Safe & Configurable**: Whitelist specific scripts to prevent accidental execution. - ⚡ **Zero-config**: Works out of the box

Node.js·MIT·★ 3·Few stars·No key

Self-custody MCP server for the Cessio RFQ desk on Canton Network — an AI agent trades as both maker and taker, holding its own party key

in the readmeany MCP client (stdio transport) — no checkout, no build: ```json { "mcpServers": { "cessio": { "command": "npx", "args": ["-y", "@cessio/agent-mcp-server"], "env": { "RFQ_BASE_URL": " "AGENT_DISPLAY_NAME": "my-agent

Node.js·MIT·Few stars·No key

Local MCP server for Weeek (stdio transport) — read-only by default, opt-in write tools.

in the readmegates.** Writes are simply not registered unless you opt in; `ENABLED_TOOLS` whitelists a subset and `MAX_RESPONSE_CHARS` caps every payload. Server-side, not client

Node.js·MIT·Few stars·Needs a key

MCP server for safe, read-only SSH diagnostics — bring your own LLM

in the readmeEvery command is read-only, and there is no arbitrary-command tool. The full whitelist is visible via `get_whitelist`. **Where does my data go?** Nowhere

Node.js·MIT·★ 1·Few stars·No key

Exposes local execution of Aider commands as a detached process using MCP.

in the readmedenied by default. ```json { "mcpServers": { "mcp-aider-executor": { "command": "npx", "args": [ "-y", "mcp-aider-executor", "--whitelist", "/home/user/my-project/**", "--whitelist", "/local/my-application/**" ], "env": { "AIDER_MODEL": "openai/gemma-4-E4B-it-IQ4_XS", "OPENAI_API_BASE

Node.js·MIT·Few stars·No key

MCP server for SSH operations with built-in diagnostics

in the readmevars, each accepting a comma-separated list of regex patterns: - `SSH_MCP_COMMAND_WHITELIST` — if set, the command **must** match at least one pattern, else

Node.js·MIT·★ 6·No key

A Model Context Protocol (MCP) server that enables secure execution of Laravel Artisan commands through Claude and other MCP clients.

in the readmeaccording to Claude): - **Directory Isolation**: Only accesses the explicitly configured Laravel directory - **Command Whitelisting**: Only executes commands that are specifically allowed - **Input Validation**: Verifies all inputs

Skill·MIT·★ 6·No key