Flagged: sudo usage, opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by peg · MCP Server · ★ 82
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is rampart safe to install? View the security audit →
Rampart A firewall for AI coding agents. Claude Code's mode, and similar autonomous modes in Cline and Codex, give agents unrestricted shell access. Your agent can read your SSH keys, exfiltrate your , or with no guardrails. Rampart sits between the agent and your system. Every command, file access, and network request is evaluated against your policy before it executes. Dangerous commands never run. Install Windows (PowerShell): After installing, run or follow the setup steps below. Quick start Pick your agent and
| Stars | 82 |
| Forks | 13 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 70.755303885515/100 |
| Open Issues | 2 |
| Last Updated | 2026-08-18 |
| Created | 2026-02-10 |
| Platforms | claude-code, cli, codex, go, mcp |
| Est. Tokens | ~20k |
Looking for a rampart alternative? If you're comparing rampart with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality ga
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis,
Explore other popular mcp server tools:
rampart is Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.. It is categorized as a MCP Server with 82 GitHub stars.
rampart is primarily written in Go. It covers topics such as agent-security, ai-agents, ai-security.
You can find installation instructions and usage details in the rampart GitHub repository at github.com/peg/rampart. The project has 82 stars and 13 forks, indicating an active community.
rampart is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to rampart on Agent Skills Hub include agentseal, agent-security-scanner-mcp, vnx-orchestration. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.