ironcurtain

by provos · TypeScript · ★ 172

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

#agent#mcp#model-context-protocol#policy#sandbox#security#trusted-process

Install

npx -y github:provos/ironcurtain

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "ironcurtain": {
      "command": "npx",
      "args": [
        "-y",
        "github:provos/ironcurtain"
      ]
    }
  }
}

From the README

[](https://github.com/provos/ironcurtain/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@provos/ironcurtain) [](LICENSE) [](https://ironcurtain.dev) **A secure\* runtime for autonomous AI agents, where security policy is derived from a human-readable constitution.** _\*When someone writes "secure," you should immediately be skeptical. [What do we mean by secure?](https://ironcurtain.dev)_ > [!WARNING] > **Research Prototype.** IronCurtain is an early-stage research project exploring how to make AI agents safe enough to be genuinely useful. APIs, configuration formats, and archit…

Read full README on GitHub →

💡 Need a managed MCP host?

Try Claude Pro for the smoothest MCP experience, or browse our cloud-hosted servers.

Related developer tools servers

everything-claude-code

affaan-m

★ 170,676

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Developer Tools · JavaScript