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.

89 starsTypeScriptMITagent-governanceai-agentai-governanceai-safety

REVIEWED74/100

Scanned 2026-07-12 · gemini v1

Dimension breakdown

Security

60/100

4 findings

Quality

95/100

5 findings

License

88/100

1 finding

Completeness

50/100

7 findings

Findings (17)

CRITICAL: 1HIGH: 2MEDIUM: 2LOW: 4INFO: 8

CRITICALcompletenessMissing server.json manifest
HIGHsecurityWeak Forbidden Pattern Matching for Commands
HIGHcompletenessTools not explicitly exposed via MCP standard
MEDIUMcompletenessMissing mcpName in package.json
MEDIUMcompletenessMissing documentation for environment variables

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/elliot35/deterministic-agent-control-protocol.svg)](https://archimedes.market/r/elliot35/deterministic-agent-control-protocol)

HTML

<a href="https://archimedes.market/r/elliot35/deterministic-agent-control-protocol"><img src="https://archimedes.market/api/badge/elliot35/deterministic-agent-control-protocol.svg" alt="Archimedes Trust Verified"/></a>