secure-edge-ai-governance
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Why this project exists
Edge AI governance is often documented as policy, diagrams, or compliance checklists. Those artifacts matter, but they do not prove that a release decision is actually enforced.
This project turns governance into executable software. A candidate release is approved only when deployment identity, two distinct human approvals, risk, drift, signature, attestation, and regression evidence satisfy deterministic policy. Any missing or failed control produces manual_hold.
The demonstrator requires the evidence record's deployment ID to match the candidate ID. Reusing an otherwise valid record from another candidate produces manual_hold. This string-level check is not cryptographic proof of artifact identity; signed artifact digests and verifier integration remain future work.
Advisory AI can recommend. Deterministic policy and accountable humans authorize.
Related MCP server: sp-devcontrol
Core engineering principle
The system deliberately separates:
probabilistic AI advice from release authority;
human accountability from automated scoring;
evidence collection from policy evaluation;
model quality from device trust; and
demo claims from production security capabilities.
The objective is not simply to predict whether a release is safe. The objective is to make the release decision inspectable, testable, fail-closed, and reproducible.
Release gate
flowchart TD
A[Deployment candidate] --> B[Deployment identity]
B --> C[Two distinct approvers]
C --> D[Risk within limit]
D --> E[Drift within limit]
E --> F[Signature valid]
F --> G[Attestation valid]
G --> H[Regression passed]
H -->|all pass| I[APPROVED]
B -->|fail| X[MANUAL HOLD]
C -->|fail| X
D -->|fail| X
E -->|fail| X
F -->|fail| X
G -->|fail| X
H -->|fail| XArchitecture
flowchart LR
A[Model / Firmware / Wasm Candidate] --> B[Cloud Control Plane]
H[Two Human Approvers] --> B
AI[Advisory AI\nRisk · Drift · Optimization] --> B
B --> G{Deterministic Governance Gate}
G -->|Approved| S[Sign / Stage Release]
G -->|Failed evidence| M[Manual Hold]
S --> T[Secure Transport + Attestation]
T --> D[Edge Device Runtime]
D --> O[Health / Drift / Telemetry]
O --> B
O -->|Failure| R[Known-good Rollback]
R --> DWhat is implemented
Capability | Implementation | Release evidence |
Deterministic release gate |
| explicit approve/manual-hold result |
Separation of duties | policy + UI + MCP | duplicate approver identities rejected |
Risk and drift gates | deterministic thresholds | out-of-policy values block release |
Signature check | release policy | invalid signature blocks release |
Attestation check | release policy | invalid evidence blocks release |
Regression gate | qualification policy | failed regression blocks release |
Governance simulator | web application | reproducible reviewer scenarios |
MCP tool surface |
| bounded governance actions |
Streamlit reviewer demo |
| portable public proof |
CI | GitHub Actions | repeatable TypeScript + Python verification |
Verify it in two minutes
Open the live Streamlit demo.
Keep all evidence valid and use two distinct approvers →
approved.Change risk above the threshold, invalidate attestation, fail regression, reuse one approver identity, or remove an approval →
manual_hold.Inspect
lib/policy.tsanddemos/streamlit/policy.pyto see the policy implemented independently in TypeScript and Python.Check GitHub Actions for repeatable verification.
MCP governance tools
The /api/mcp JSON-RPC surface exposes bounded governance operations:
Tool | Purpose |
| validate deployment identity and approver separation |
| execute the fail-closed release policy |
| create an explicit hold with reason and next action |
An AI agent may call these tools, but it cannot override the deterministic policy implemented inside them.
Security boundary
Implemented as executable controls:
deterministic fail-closed decision logic;
two-person approval semantics;
risk and drift limits;
signature, attestation, and regression evidence checks;
explicit hold reasons; and
independent CI verification.
Not represented as completed production infrastructure:
identity-provider authorization;
hardware-backed TPM/TEE quote verification;
HSM/KMS production release signing;
production mTLS lifecycle;
append-only audit storage;
real OTA fleet orchestration; and
production rollback execution.
See docs/SECURITY_MODEL.md for the hardening path.
Run locally
git clone https://github.com/h00w/secure-edge-ai-governance.git
cd secure-edge-ai-governance
npm ci
npm run lint
npm test
npm run devStreamlit reviewer demo:
cd demos/streamlit
python -m pip install -r requirements.txt
python -m pytest -q
python -m streamlit run app.pyProof chain
Architecture → Policy → Interactive UI → MCP Tool Surface → Tests → CI → Documentation → Live Demo
Architecture:
docs/ARCHITECTURE.mdSecurity model:
docs/SECURITY_MODEL.mdDemo guide:
docs/DEMO_GUIDE.md
Author
Hendarmawan, PhD Eng.
AI Engineering · Secure Edge AI · Trusted Computing · AI Governance · Production AI
Production AI proof level
This repository uses the shared Production AI Five-Level Proof Model v1:
L1 Runnable → L2 Reproducible → L3 Capability-Validated → L4 Production-Candidate → L5 Production-Validated.
Run make proof to generate the machine-readable assessment. The repository deliberately caps its current claim at L3 — Capability-Validated; the public reviewer surface and deterministic policy tests are evidence of capability, not proof of hardware-backed or fleet-production deployment.
See PROOF_MODEL.md and REPRODUCIBILITY.md.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Governed MCP workflow automation for MSPs and agencies: approvals, durable state, signed evidence.
Deterministic IT asset registry operated by AI agents over MCP. Agents propose, humans approve.
Related MCP Servers
AlicenseAqualityDmaintenanceGovernance circuit-breaker MCP server that enables AI agents to request risk-based decisions, approve or deny actions, and finalize outcomes with full audit receipts.4MIT- AlicenseNot gradedqualityCmaintenanceLocal governance layer for AI-assisted development, providing human authorization gates, policy enforcement, change approval workflow, and rollback capabilities through a universal MCP server.MIT
- FlicenseNot gradedqualityCmaintenanceProvides governed MCP tools for a controlled, AI-assisted asset-change pipeline, featuring natural-language requests, mandatory approvals, execution-time revalidation, and complete audit.-
- AlicenseNot gradedqualityDmaintenanceEnables governing tenant-aware MCP tools with policy enforcement, scoped access, human approval workflows, and tamper-evident audit logging.MIT