MCP Catalogs
Homedeterministic-agent-control-protocol screenshot

deterministic-agent-control-protocol

by elliot35·86·Score 46

A governance gateway for AI agents providing bounded, auditable control via MCP proxy, shell proxy, and HTTP API.

developer-toolssecurityai-llm
6
Forks
0
Open issues
3 mo ago
Last commit
2d ago
Indexed

Overview

The Deterministic Agent Control Protocol (Det-ACP) serves as a governance layer for AI agents, ensuring every action is bounded, auditable, reversible, and explainable. It works transparently with popular AI coding environments like Cursor, Claude Code, and Codex while providing a policy-based enforcement system that prevents harmful operations like deleting sensitive files or executing dangerous commands. The protocol supports multiple integration modes including MCP proxy for transparent tool interception, shell proxy for command governance, and HTTP API for language-agnostic integration.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Securing AI agents by preventing access to sensitive files and secrets
you:Providing audit trails for all agent actions in enterprise environments
you:Enforcing organizational policies on development and deployment workflows
you:What agents are compatible with Det-ACP?
you:How does the policy system work?

When to choose this

When you need to govern AI agents with strict access controls, audit trails, and policy enforcement for sensitive operations.

When NOT to choose this

If you're working with open-source LLMs not connected to MCP clients, or if you need minimal governance overhead.

Tools this server exposes

9 tools extracted from the README
  • create_session

    Create a new governance session with a specified policy

  • evaluate

    Evaluate an action against governance policy without executing it

  • record_result

    Record the result of an evaluated action in the audit ledger

  • terminate_session

    End a governance session and generate an activity report

  • proxy

    Start an MCP proxy that intercepts and governs tool requests

  • exec

    Execute a shell command through the governance proxy

  • validate

    Validate a policy configuration file for syntax and rules

  • report

    Generate an audit report from a ledger file

  • serve

    Start an HTTP session server for governance API access

Note: Tools inferred from API examples and CLI commands, as no explicit 'Tools' section was found in the documentation. The actual MCP tools would likely be the underlying tools being governed (like file operations, commands, etc.) but these are

Comparable tools

agent-governance-mcpai-safety-proxypolicy-based-agent

Installation

Installation

npm install @det-acp/core

Quick Start

Initialize governance for your AI agent:

npx det-acp init cursor        # For Cursor
npx det-acp init codex         # For Codex CLI
npx det-acp init claude-code   # For Claude Code

Configure Claude Desktop (if applicable):

{
  "mcpServers": {
    "det-acp": {
      "command": "npx",
      "args": ["-y", "@det-acp/core"]
    }
  }
}

FAQ

What agents are compatible with Det-ACP?
Det-ACP works with Cursor, Claude Code, Codex, and any MCP-compatible agent. It also supports shell-based agents through its shell proxy mode.
How does the policy system work?
Policies are defined in YAML files specifying allowed tools, paths, session limits, risk thresholds, and forbidden patterns. The protocol evaluates every action against these policies before execution.

On Hacker News

Recent discussion from the developer community.

Compare deterministic-agent-control-protocol with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.