ironcurtain MCP Server
provos/ironcurtain
[](https://agentrank-ai.com/tool/provos--ironcurtain/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
provos/ironcurtain is a TypeScript tool licensed under Apache-2.0. A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev) Topics: agent, mcp, model-context-protocol, policy, sandbox, security, trusted-process.
Ranked #898 out of 24849 indexed tools.
In the top 4% of all indexed tools.
Has 10 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
613 stars → growing community
Last commit today → actively maintained
25/36 issues closed → decent issue management
10 contributors → active community
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
# IronCurtain **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 architecture may change. Contributions and feedback are welcome. ## Demo <p align="center"> </p> The agent is asked to clone a repository and push changes. Both `git_clone` and `git_push` are escalated by the policy engine, but the auto-approver approves them automatically — the user's trusted input from command mode (Ctrl-A) provided clear intent, so no manual `/approve` was needed. ## The Problem Autonomous AI agents can manage files, run git commands, send messages, and interact with APIs on your behalf. But today's agent frameworks givRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.