AI-Native Open-source Casino Platform FrameworkBLOCK
Open-source Casino Platform Framework - AI-Native, Self-hosted, Headless, Plugin-based 🎰
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/blurifycom/openora/actions/workflows/pipeline.yml) [](https://www.npmjs.com/package/@openora/core) [](https://www.npmjs.com/package/@openora/core?activeTab=versions) [](./LICENSE) [](#requirements) [](#requirements) [](./CONTRIBUTING.md) [](./CODEOFCONDUCT.md) [](https://github.com/blurifycom/openora/discussions)
Open-source, headless, plugin-based, AI-native Casino Platform Framework. Clone it, extend it, deploy it - without forking core.
The platform ships the backend surface (auth, wallet, player management, compliance, audit, chat, backoffice) as composable modules and a typed SDK. Game lobby and CMS are early; bonuses, tournaments, affiliates and jackpots are not built yet - the order is being picked in Discussions. Your frontend, branding, and vendor adapters live in your own consumer repo and talk to it over HTTP. Nothing operator-specific lives here.
[!WARNING] Status: alpha (pre-1.0). Contracts, package layout, and APIs may change between releases. Not yet recommended for production without your own review. See the roadmap.
Highlights
- **Headless
6c9c84d54f65OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add testing --env PAYMENT_WEBHOOK_SECRET=${PAYMENT_WEBHOOK_SECRET} -- npx -y @openora/[email protected]{
"mcpServers": {
"testing": {
"command": "npx",
"args": [
"-y",
"@openora/[email protected]"
],
"env": {
"PAYMENT_WEBHOOK_SECRET": "${PAYMENT_WEBHOOK_SECRET}"
}
}
}
}Exposed tools (26)
24 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
catalog-overview | read | |
db-query-readonly | read | |
describe-module | read | |
docs-search | read | |
enhance-intent | read | |
get-config-schema | read | |
get-drizzle-schema | read | |
impact | read | |
legacy_lookup | read | Legacy lookup |
list-adapters | read | |
list-agent-tools | read | |
list-events | read | |
list-extension-points | read | |
list-modules | read | |
list-routes | read | |
list-slash-commands | read | |
propose-table-change | read | |
read-agents-md | read | |
regen | read | |
run-verify | write | |
scaffold-app | read | |
scaffold-module | read | |
scaffold-plugin | read | |
scaffold-route | read | |
schema-get | read | |
start | write |
Trust audit
BLOCKgrade F · trust 57/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (1 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
mail-payload.service.ts
DATABASE_URL=postgresql://postgres:postgres@localhost:5432/oss_igaming
redis-pubsub-realtime-transport.ts
DATABASE_ADMIN_URL: postgres://postgres:postgres@localhost:5432/oss_igaming_test
DATABASE_URL: postgres://postgres:postgres@localhost:5432/oss_igaming_test
TEST_ADMIN_DATABASE_URL: postgresql://postgres:postgres@localhost:5432/postgres
TEST_DATABASE_URL: postgres://postgres:postgres@localhost:5432/oss_igaming_test
token: 'minted-session-token',
password: 'stored-password-hash',
token: 'active-session-token',
token: 'other-active-session-token',
password: 'stored-password-hash',
.dependency-cruiser.cjs
.oxfmtrc.json
.oxlintrc.json
files: ['../../extensions.config.ts'],
join(core, '../../node_modules/.bin/drizzle-kit'),
import { mock, testContext, makeAuditWriter, makeAdminGuard } from '../../testing/mock.js';import { mock } from '../../testing/mock.js';import { mock, adminCaller, testContext } from '../../testing/mock.js';`POST /compliance/kyc/webhook` is unauthenticated (M2M, no admin session) and relies
`prefetchLobby`, `prefetchGames`, `prefetchWallet`, etc., live in `packages/sdks/react-sdk/src/server/`. They run server-only (no `'use client'`, no React tree), build an oRPC client via `@openora/sdk
You are a senior backend TypeScript engineer (Hono, oRPC, Drizzle) building the OSS igaming platform. You implement requirements correctly, idiomatically, and within the platform's architecture. The p
You are a senior iGaming product/domain expert who has shipped multiple real-money platforms: player journeys, game mechanics, RGS/provably-fair, payments (PSP + crypto), KYC/AML, responsible gaming,
You are a senior code-quality reviewer for this repo. One pass over the changed files, several lenses. You are NOT the implementer - findings only, no changes.
Gates applied: no_behavioural_pass.
6c9c84d54f65full audit observations/trust-audit/mcp-server/blurifycom__openora.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 6c9c84d54f65 | BLOCK | F | 57 | first audit |
Questions
What is the @openora/mcp MCP server?
Open-source Casino Platform Framework - AI-Native, Self-hosted, Headless, Plugin-based 🎰
What tools does @openora/mcp expose?
26 in total: 24 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @openora/mcp safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (57/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does @openora/mcp need?
It reads PAYMENT_WEBHOOK_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does @openora/mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @openora/testing at 0.4.0.
How current is this page?
The grade is for one exact copy of the source (6c9c84d54f65), read on 2026-10-12. The repository is watched and re-audited when it changes.