
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.
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:
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 READMEcreate_sessionCreate a new governance session with a specified policy
evaluateEvaluate an action against governance policy without executing it
record_resultRecord the result of an evaluated action in the audit ledger
terminate_sessionEnd a governance session and generate an activity report
proxyStart an MCP proxy that intercepts and governs tool requests
execExecute a shell command through the governance proxy
validateValidate a policy configuration file for syntax and rules
reportGenerate an audit report from a ledger file
serveStart 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
Installation
Installation
npm install @det-acp/coreQuick 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 CodeConfigure 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.
- Story by elliot35 · 2026-02-10
Compare deterministic-agent-control-protocol with
Last updated · Auto-generated from public README + GitHub signals.