AgentIndex icon
AgentIndex
ironcurtain logo
ironcurtain
★ 614
vs
mcpproxy-go logo
mcpproxy-go
★ 398

ironcurtain vs mcpproxy-go

ironcurtain: IronCurtain provides a secure runtime for autonomous AI agents, enforcing security policies derived from human-readable constitutions to prevent issues like prompt injection. It ensures agents operate within defined boundaries through mechanisms like V8 isolates and a policy engine that mediates all tool calls.; mcpproxy-go: MCPProxy is an open-source smart proxy application designed to enhance AI agents by providing intelligent tool discovery, significant token savings, and robust security features. It enables agents to scale beyond API limits, protect against malicious attacks, and integrates seamlessly across various platforms and AI development environments.

01

TL;DR

ironcurtain logo
ironcurtainSecurity & Safety · ★ 614

Securely Automating Development Tasks: Allowing AI agents to manage files and execute Git operations like cloning and pushing changes within defined security boundaries.

Read ironcurtain full review →
mcpproxy-go logo
mcpproxy-goSecurity & Safety · ★ 398

Federate multiple MCP servers to provide AI agents with a vast array of tools, bypassing inherent API limitations.

Read mcpproxy-go full review →
02

Side-by-Side Comparison

Field
ironcurtain logoironcurtain
mcpproxy-go logomcpproxy-go
Category
Security & Safety
Security & Safety
Stars
★ 614
★ 398
License
Apache-2.0
MIT
Install Command
npm install -g @provos/ironcurtain
go install github.com/smart-mcp-proxy/mcpproxy-go/cmd/mcpproxy@latest
Updated
2d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agents, Security, Runtime
AI Proxy, Agent Framework, Tool Discovery
03

Features

ironcurtain logoironcurtain
01Constitution-driven Security Policy: Define security intent in plain English, which is then compiled into deterministic and enforceable rules.
02Semantic Interposition & Runtime Enforcement: All agent interactions and tool calls are routed through a policy engine that allows, denies, or escalates based on policy.
03Untrusted Agent Model: Assumes the LLM may be compromised (e.g., by prompt injection or drift), enforcing security at the boundary regardless of the model's behavior.
04Multi-mode Operation: Supports both an internal LLM agent running in a V8 sandbox (Code Mode) and external agents running in Docker containers (Docker Agent Mode).
05Built-in Capabilities: Ships with pre-configured MCP servers for filesystem, Git, web fetching, and GitHub operations, all governed by policy.
mcpproxy-go logomcpproxy-go
01Scale beyond API limits by federating hundreds of MCP servers and bypassing tool/function caps.
02Achieve massive token savings and accelerate responses with efficient tool schema loading.
03Advanced security protection with automatic quarantine against Tool Poisoning Attacks.
04Works offline and cross-platform with native binaries for macOS, Windows, and Linux.
05Secure secrets management using OS-native keyring for API keys and credentials.
06Docker security isolation for stdio MCP servers, ensuring process and file system isolation.
04

Use Cases

ironcurtain logoironcurtain
↳Securely Automating Development Tasks: Allowing AI agents to manage files and execute Git operations like cloning and pushing changes within defined security boundaries.
↳Autonomous Code Management and Bug Fixing: Utilizing agents to fix failing tests or perform code modifications in a project workspace with robust policy enforcement.
↳Controlled API Interactions: Enabling agents to interact with web services (e.g., web search, GitHub APIs) with granular policy control over each specific API call.
↳Managing AI Agent Security in Complex Environments: Running external AI agents (e.g., Claude Code, Goose) securely within a Docker container, with IronCurtain mediating every tool call through its policy engine.
↳Remote Agent Control and Escalation Handling: Interacting with and approving agent actions via end-to-end encrypted messaging platforms like Signal.
mcpproxy-go logomcpproxy-go
↳Federate multiple MCP servers to provide AI agents with a vast array of tools, bypassing inherent API limitations.
↳Protect AI agents from malicious MCP servers and Tool Poisoning Attacks through security quarantines.
↳Integrate seamlessly with popular IDEs and AI tools like Cursor, VS Code, and Claude Desktop to enhance development workflows.
↳Securely manage and inject API keys and other sensitive credentials for various MCP servers using the OS-native keyring.
↳Run stdio-based AI agent tools in isolated Docker containers for enhanced security and resource management.
FAQ

FAQ

What is the difference between ironcurtain and mcpproxy-go?
Both ironcurtain and mcpproxy-go are in the Security & Safety category. ironcurtain has 614 stars, while mcpproxy-go has 398 stars.
Which is better, ironcurtain or mcpproxy-go?
The best choice depends on your use case. Choose ironcurtain if Securely Automating Development Tasks: Allowing AI agents to manage files and execute Git operations like cloning and pushing changes within defined security boundaries., and mcpproxy-go if Federate multiple MCP servers to provide AI agents with a vast array of tools, bypassing inherent API limitations..
Is ironcurtain free or open source?
Yes, ironcurtain is open source on GitHub (Apache-2.0).
Is mcpproxy-go free or open source?
Yes, mcpproxy-go is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to ironcurtain →Alternatives to mcpproxy-go →ironcurtain details →mcpproxy-go details →