elliot35/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.

39
/ 100
Emerging

This tool helps AI engineers and developers set guardrails for AI agents, ensuring they operate within defined boundaries. You provide it with a policy specifying what an agent can and cannot do, and it acts as a gateway, approving or denying agent actions. This allows developers to safely deploy agents without worrying about unintended behaviors like data exfiltration or unauthorized system changes.

145 stars.

Use this if you need to ensure AI agents operate securely and predictably within your systems, preventing them from accessing forbidden files or executing risky commands.

Not ideal if you are looking for a tool that executes agent actions itself, as this protocol only evaluates and records actions, leaving execution to other systems.

AI Governance Agent Security AI Safety Developer Tooling API Security
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 8 / 25

How are scores calculated?

Stars

145

Forks

6

Language

TypeScript

License

MIT

Last pushed

Feb 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/elliot35/deterministic-agent-control-protocol"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.