MCP Vetted

deterministic-agent-control-protocol

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.

Repository
elliot35/deterministic-agent-control-protocol
Stars
88
Last push
2026-02-12
License
MIT
Category
Security

Score breakdown — how scoring works

  • Maintenance

    10.5 / 30
    • Pushed within 8 months141 days ago+10.5

  • Adoption

    11.3 / 25
    • GitHub stars (no package published — stars weighted fully)88+11.3

  • Documentation

    20 / 25
    • Comprehensive README (6,000+ chars)29261 chars+10
    • Install / setup instructionsyes+6
    • Tools / capabilities documentedno+0
    • Code or client-config exampleyes+4

  • Trust signals

    7 / 20
    • OSS license declaredMIT+7
    • First-party vendor implementationno+0
    • DNS-verified registry namespaceno+0
    • Listed in official MCP Registryno+0
    • Owned by an organizationno+0

Install

From sourcegit clone https://github.com/elliot35/deterministic-agent-control-protocol

No package published to a registry — see the README for setup instructions.

Always review a server's code and required credentials before connecting it to your MCP client. MCP Vetted scores public metadata — it does not audit code for malicious behavior (yet). Methodology →

View on GitHub ↗