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.
Implements a control plane that intercepts all agent tool calls against a YAML policy, supporting real-time decisions (allow/deny/gate) with session-level budgets and rate limits. Provides three integration modes: MCP proxy for native support in Cursor/Claude Code, shell proxy for OS-level command governance, and HTTP API for language-agnostic agents. Records tamper-evident audit trails with SHA-256 hash chaining and enables policy self-evolution through automated rule refinement based on interaction history.
145 stars.
Stars
145
Forks
6
Language
TypeScript
License
MIT
Category
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.
Higher-rated alternatives
AndrewAltimit/template-repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows,...
Chimera-Protocol/csl-core
Deterministic safety layer for AI agents. Z3-verified policy enforcement.
agentralabs/agentic-contract
Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation...
portofcontext/pctx
pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers...
behrensd/mcpwall
Deterministic security proxy for MCP tool calls — iptables for MCP