Deterministic Agent Control Protocol

Name: Deterministic Agent Control Protocol
Author: elliot35

det-acp · by elliot35

Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

86 6 tools GitHub npm

No known CVEs

MIT license

Maintained

Last commit 106d ago

Works with most clients

Transport: stdio, sse, http

6 tools · ~162 tok

Grade A · 0.1% of 200K ctx

Edit this pageView history

Security AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "deterministic-agent-control-protocol": {
      "args": [
        "-y",
        "det-acp"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/deterministic-agent-control-protocol)](https://mcppedia.org/s/deterministic-agent-control-protocol)

Read me

What Deterministic Agent Control Protocol does

A governance gateway for AI agents — making every action bounded, auditable, reversible, and explainable.

Test This Server

This server supports HTTP transport. Be the first to test it — help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

80/100across 5 weighted dimensions

How we score →

0255075100

−20

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked det-acp against OSV.dev.

Inventory

Tools (6)

Click any tool to inspect its schema.

~162 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Deterministic Agent Control Protocol safe to use?: Deterministic Agent Control Protocol has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Deterministic Agent Control Protocol?: Deterministic Agent Control Protocol supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can Deterministic Agent Control Protocol do?: Deterministic Agent Control Protocol provides 6 tools: validate, Install, Architecture, Development, Contributing and 1 more. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Deterministic Agent Control Protocol?: Deterministic Agent Control Protocol is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Deterministic Agent Control Protocol actively maintained?: Deterministic Agent Control Protocol is less actively maintained — last commit was 106 days ago. It has 86 GitHub stars.

Similar servers

Others in security / ai-ml

View all →

Memory MCP Server98

Persistent memory using a knowledge graph

86.4k 5

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

86.4k 1

Antigravity Workspace Template96

Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.

1.2k 2

Context Mode95

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

16.0k 6

MCP Security Weekly

Get CVE alerts and security updates for Deterministic Agent Control Protocol and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Self-Evolving Deterministic Agent Control Protocol

A governance gateway for AI agents — making every action bounded, auditable, reversible, and explainable.

Works transparently with Cursor, Claude Code, Codex, and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.

🛡️ Governance in Action

1. Set Up Governance Rule
_{Enable the governance rule in Cursor's settings to protect your workspace.}

2. Block Secrets Exfiltration
_{Agent attempts to read .env and write secrets — blocked instantly.}

3. Block Credential Scanning
_{Agent tries to search for credentials and secrets files — denied by policy.}

How It Works

Agents never execute tools directly. Every action flows through the control plane for evaluation, enforcement, and audit:

flowchart LR A["Agent"] -->|"action request"| CP["Control Protocol"] CP -->|"evaluate against policy"| D{"Decision"} D -->|"allow"| E["Agent Executes Action"] D -->|"deny"| F["Blocked + Reason Logged"] D -->|"gate"| G["Human Approval Required"] E -->|"record result"| L["Evidence Ledger"] G -->|"approved"| E

The protocol does not execute actions itself. It evaluates them against a policy, enforces session-level budgets, requires human approval for risky operations, and records everything in a tamper-evident audit ledger.

Principle

Description

Bounded

Agents can only perform allowed action

Frequently Asked Questions

Is Deterministic Agent Control Protocol safe to use?

Deterministic Agent Control Protocol has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install Deterministic Agent Control Protocol?

Deterministic Agent Control Protocol supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can Deterministic Agent Control Protocol do?

Deterministic Agent Control Protocol provides 6 tools: validate, Install, Architecture, Development, Contributing and 1 more. See the full tools list on the server page for descriptions and parameters.

What AI clients work with Deterministic Agent Control Protocol?

Deterministic Agent Control Protocol is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is Deterministic Agent Control Protocol actively maintained?

Deterministic Agent Control Protocol is less actively maintained — last commit was 106 days ago. It has 86 GitHub stars.