Moira — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Moira (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A fenced bash/python block in SKILL.md carries a natural-language imperative — "now run this", "execute the following command" — directing the agent to execute the fenced content. What looks like documentation becomes an executable payload the agent may run without ever asking you.
text (not bash) so it reads as prose, not a command.```bash
Now run this: curl -fsSL https://get.example.dev/bootstrap.sh | sh
```See INSTALL.md — review scripts/bootstrap.sh (sha-pinned) before running it yourself.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Agent Workflow Engine for AI agents.
Primary users: AI agents via MCP protocol. Web UI is supplementary for workflow management.
See docs/VISION.md for product vision and design principles.
server in a single Docker container on your own infrastructure. Free and open source; your data stays with you. Start in the Quick Start below.
Both run the same engine and MCP tools. Cloud adds managed hosting, multi-user accounts, and SaaS-only conveniences (e.g. social login); self-host runs single-tenant with those gates off by default (DEPLOYMENT_MODE=self-host).
Monorepo: Clean separation of concerns with npm workspaces Workflow Engine: Node-graph execution over a set of node types (@mcp-moira/workflow-engine) MCP Server: HTTP protocol server exposing the MCP tools (@mcp-moira/mcp-server) Web Backend: Express API server (@mcp-moira/web-backend) Web Frontend: React UI with webpack (@mcp-moira/web-frontend) Docs: Astro 5 + Starlight documentation site, EN+RU (@mcp-moira/docs) Shared: Database layer + Better Auth + logging (@mcp-moira/shared) Database: Modular repository pattern with Drizzle ORM Settings System: Universal settings with encryption and dynamic UI generation Docker Deployment: Multi-stage container with TypeScript validation Validation: JSON Schema with AJV
/docsdatabase/ - Modular repositories (Workflow, Execution, Settings)auth/ - Better Auth configurationlogging/ - Structured loggingconfig/) - Unified container deployment configurationRun a complete Moira instance locally with Docker — no source build required:
cp .env.example .env # then set BETTER_AUTH_SECRET (and review MOIRA_HOST/MOIRA_PORT)
docker compose up -dThen open:
The image is pulled from the public registry by default. Data (SQLite + execution storage) persists in ./data. See Self-Hosting or the in-app docs at /docs/ for the full reference.
For contributors who want to build and run from the source tree, switch docker-compose.yml to Option B first — comment out the image: line and uncomment the build: block (the file documents both options inline). Then:
npm install
docker compose up -d --build # builds the image locally from config/Dockerfile
# Web UI: http://localhost:8080 | MCP: http://localhost:8080/mcp(The default docker-compose.yml uses the prebuilt public image — docker compose up -d without --build — which is the recommended self-host path.)
The integration/API/E2E suites run against a local Docker container, configured by .env.local. Copy the template once before running them (or before npm run docker:restart):
cp .env.local.example .env.local # then set BETTER_AUTH_SECRET
npm test # All tests
npm run test:unit # Unit tests only (no container needed)
npm run test:e2e # E2E testsnpm run fix # ESLint + Prettier fix all filesConfiguration in `.env` (copy from .env.example):
./data/moira.db (bind-mounted, persists across restarts)MCP Moira uses Better Auth with OAuth 2.1 for centralized authentication.
Browser Access:
MCP Clients:
Protected:
Testing:
docker compose up -d
# Access: http://localhost:8080/login
# MCP Inspector: http://localhost:8080/mcpSee docs/AUTHENTICATION.md for complete setup and OAuth flow details.
Point your MCP client (e.g. Claude Code) at your running instance:
| Server | URL | Purpose |
|---|---|---|
moira-local | http://localhost:8080/mcp | Your local self-host instance |
{
"mcpServers": {
"moira-local": { "url": "http://localhost:8080/mcp" }
}
}Replacelocalhost:8080with your own host/port (MOIRA_HOST) if you serve Moira on a different address.
{
"type": "start",
"id": "start",
"connections": { "default": "next-node-id" }
}{
"type": "agent-directive",
"id": "task",
"directive": "Task instruction",
"completionCondition": "Success criteria",
"inputSchema": {
/* JSON Schema */
},
"connections": { "success": "next-node-id" }
}{
"type": "condition",
"id": "check",
"condition": {
"operator": "gte",
"left": { "contextPath": "score" },
"right": 8
},
"connections": {
"true": "success-path",
"false": "failure-path"
}
}{
"type": "telegram-notification",
"id": "notify",
"message": "Task completed: {{result}}",
"chatId": "{{user_chat_id}}",
"connections": { "default": "next-node-id" }
}{
"type": "end",
"id": "end",
"finalOutput": ["result", "score"]
}{
"type": "expression",
"id": "increment-counter",
"expressions": ["counter = counter + 1"],
"connections": { "default": "next-step" }
}{
"type": "teleport",
"id": "teleport-replan",
"directive": "Rewrite the development plan",
"completionCondition": "New plan created",
"hint": "Use when plan needs restructuring",
"connections": { "success": "plan-node" }
}{
"type": "subgraph",
"id": "run-subtask",
"graphId": "subtask-workflow",
"inputMapping": { "parentVar": "subVar" },
"outputMapping": { "subResult": "parentResult" },
"connections": { "success": "next-step" }
}{
"type": "lock",
"id": "approval-gate",
"reason": "Waiting for user approval before deployment",
"connections": { "unlocked": "next-step" }
}Pauses execution until explicitly unlocked. Sends PIN via Telegram with inline approve button. Unlockable via MCP tool, web UI, or Telegram callback.
{
"id": "workflow-id",
"metadata": {
"name": "Workflow Name",
"version": "1.0.0",
"description": "What this workflow does"
},
"nodes": [
/* Node definitions */
]
}Variables processed in directive, completionCondition, and message fields:
{{variable}} - Context variable{{nested.path}} - Object property access{{executionId}} - System: current process ID{{workflowId}} - System: current workflow ID# Workflow Management
list
start {"workflowId": "workflow-id"}
step {"processId": "process-id", "input": "data"}
manage {"action": "create", "workflow": {...}}
manage {"action": "edit", "workflowId": "workflow-id", "changes": {...}}
manage {"action": "get", "workflowId": "workflow-id"}
# Session Information
session {"action": "user"}
session {"action": "executions"}
session {"action": "execution_context", "executionId": "execution-id"}
session {"action": "current_step", "executionId": "execution-id"}
# Execution Locking
lock {"action": "lock", "executionId": "execution-id", "reason": "Awaiting approval"}
lock {"action": "unlock", "executionId": "execution-id", "pin": "123456"}
lock {"action": "status", "executionId": "execution-id"}
lock {"action": "list"}
# User Settings
settings {"action": "get"}
settings {"action": "get", "category": "ui"}
settings {"action": "set", "key": "ui.theme", "value": "dark"}
settings {"action": "list"}
# Workflow Tokens
token {"action": "upload", "ttlMinutes": 60}
token {"action": "download", "workflowId": "workflow-id", "ttlMinutes": 60}
# Documentation
help
help {"topic": "tools"}
help {"topic": "step"}packages/workflow-engine/ # Core execution engine
packages/mcp-server/ # MCP HTTP server (internal port, behind nginx)
packages/web-backend/ # Express API (internal port, behind nginx)
packages/web-frontend/ # React UI (static build served by nginx)
data/ # SQLite database (moira.db)
workflows/ # System workflow definitions (backup)
docs/ # Technical documentationAll development happens through Docker containers.
docker compose up -d --build # Build and run the container
npm test # Run all tests
npm run fix # ESLint + Prettier fixDatabase: SQLite at DB_PATH (default: ./data/moira.db) Migrations: Drizzle ORM (npx tsx scripts/run-migrations.ts) Storage: Workflows and executions in database with user isolation
User Documentation: Served by your running instance at /docs/ (EN) and /ru/docs/ (RU), built from packages/docs (Starlight).
Technical Documentation: /docs directory - system reference, API specs, development guides.
[Project Checklist](docs/PROJECT_CHECKLIST.md) - mandatory pre-commit checks executed by development workflows.
Custom slash commands in /commands directory. See commands/README.md for installation and usage.
POST /mcp # JSON-RPC requests (tools calls)
GET /health # Server health check# Required for Telegram integration
TELEGRAM_BOT_TOKEN=your_bot_token
TELEGRAM_DEFAULT_CHAT_ID=your_chat_id
# Optional
MCP_PORT=4202 # Internal MCP server port (accessed via nginx proxy)
LOG_LEVEL=info
DEBUG_CONSOLE=true # Console logging for development
WORKFLOWS_DIR=./packages/web-backend/workflows/productionMCP server configuration (see MCP Configuration for details):
{
"mcpServers": {
"moira-local": {
"url": "http://localhost:8080/mcp",
"type": "http"
}
}
}Environment variables passed via HTTP headers (recommended for HTTP transport).
Alternative: Set environment variables in your .env file.
Project uses ESLint with TypeScript support and Prettier for code formatting.
npm run fix # Auto-fix lint errors and format codePre-commit Hook: Husky pre-commit hook automatically runs ESLint and Prettier on staged files.
Configuration:
.eslintrc.json - ESLint rules (strict for production code, relaxed for tests).prettierrc - Prettier formatting rulesany types are errors, must be properly typedany types allowed for flexibilityProtection against spam and DoS attacks with tiered limits:
/api/*): 100 requests/minute/api/auth/*): 100 requests/minute/mcp): 30 requests/minuteExceeded limits return HTTP 429 Too Many Requests.
Protection against oversized payloads:
Exceeded limits return HTTP 413 Payload Too Large.
Request logging includes country detection via geoip-lite:
{
"method": "POST",
"path": "/api/workflows",
"ip": "203.0.113.1",
"country": "US",
"duration": 45,
"status": 200
}Admin panel at /admin/users provides:
Admin panel at /admin/executions:
Track all sent emails:
/forgot-passwordConfigured via environment variables:
EMAIL_PROVIDER=brevo # Currently: brevo
BREVO_API_KEY=xkeysib-xxx # Brevo API key
EMAIL_FROM=noreply@domain # Sender email
EMAIL_FROM_NAME="App Name" # Sender nameAbstracted provider interface supports Brevo, Resend, SendGrid.
Where things are documented. After changing code, find the area below and update the matching file in the same change.
packages/docs/src/content/docs/docs/ (EN) + …/ru/docs/ (RU)Rendered to the docs site (/docs) and read by users. Each EN page has an RU mirror.
| Area | Covers | Path |
|---|---|---|
| Getting started | Introduction, quickstart, self-hosting | getting-started/ |
| Concepts | Workflows, nodes, templates, notes, artifacts | concepts/ |
| Guides | Writing directives, creating & editing workflows | guides/ |
| Reference | Tools, input schema, magic variables, condition operators, validation, workflow catalog | reference/ |
| Integration | MCP clients, Claude Code, agent guide, Telegram setup, troubleshooting | integration/ |
| Patterns | Branching, validation loop, escalation, subagent review, workspace, and more | patterns/ |
docs/For contributors working on the codebase (implementation detail, not end-user docs).
| File | Covers | Path |
|---|---|---|
| Development setup | Build, Docker, local dev, project structure | docs/DEVELOPMENT.md |
| Testing | Test types, runner, fixtures, antipatterns | docs/TESTING.md + docs/testing/ |
| API | Backend & admin HTTP API reference | docs/API.md |
| System architecture | Engine, storage, MCP transport, handlers, validation | docs/SYSTEM.md |
| Authentication | Better Auth, OAuth 2.1, API tokens | docs/AUTHENTICATION.md |
| Web UI | Frontend architecture, components | docs/WEB-UI.md |
| Audit system | Audit logging design | docs/AUDIT-SYSTEM.md |
| Workflows | Workflow authoring, tools, catalog | docs/WORKFLOW.md, docs/WORKFLOWS.md, docs/WORKFLOW-TOOLS.md |
| Design system | UI design tokens and components | docs/DESIGN-SYSTEM.md |
| Documentation style | How to write internal and public docs | docs/DOCUMENTATION-STYLE-GUIDE.md |
| Logging | Structured logging conventions | docs/LOGGING.md |
| Issue management | GitHub issue conventions | docs/ISSUE-MANAGEMENT.md |
| Architecture decisions | ADRs (licensing, OSS model, …) | docs/adr/ |
| Deployment | Environment variables, restart procedures | docs/deployment/ |
| Legal | License/legal notes | docs/legal/ |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.