StableDeliver AI Bridge
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@StableDeliver AI Bridgerun the test suite and report results"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
StableDeliver AI Bridge
Private infrastructure. Not a public product. Not the StableDeliver customer product.
The StableDeliver AI Bridge is a small, private, MCP-compatible server that lets ChatGPT (acting as supervisor/reviewer) drive Claude Code (acting as the engineering worker) through a controlled, logged, safety-gated interface.
ChatGPT (supervisor)
↓ MCP over HTTPS
https://bridge.stabledeliver.com/mcp
↓
StableDeliver Bridge Server (Node.js + TypeScript)
↓ controlled task files
Claude Code CLI / Claude Agent SDK
↓
GitHub repo + workspace + tests + Coolify staging
↓
Reports & logs back to the bridge
↓
ChatGPT reviews and decides the next actionWhat this bridge IS
A private automation bridge so ChatGPT can supervise Claude Code.
A controlled task queue + execution + reporting system.
Safety-gated: read/plan/edit/staging only, with owner approval for anything risky.
Related MCP server: ChatGPT-Codex-Claude Bridge
What this bridge is NOT
It is not the StableDeliver customer product.
It does not verify USDT/USDC payments.
It does not deliver digital products.
It does not custody funds, move funds, exchange tokens, or hold private keys.
It does not touch production, DNS, billing, or wallets without explicit owner approval.
Roles
Role | Who | Responsibility |
Engineering worker | Claude Code | Writes code, runs tests, creates reports — within safety limits |
Supervisor / reviewer | ChatGPT | Reviews reports, decides next task, approves/rejects phases |
Owner | Khaled | Holds accounts & money, approves DNS/deploy/spend/production |
See PROJECT_RULES.md for the full role contract.
Endpoints (planned)
Method | Path | Auth | Purpose |
GET |
| admin token | Private dashboard (status only, no secrets) |
GET |
| none | Health check JSON |
POST |
| bearer/connector | MCP endpoint exposing bridge tools |
GET |
| admin token | Recent logs (optional) |
MCP tools (v0.1)
Tool | Risk | Auto-allowed |
| Low | Yes |
| Low | Yes |
| Low | Yes |
| Medium | Yes, if no blocked actions |
| Medium/High | Plan/read/edit only |
| Medium | Yes |
| High | No — owner approval |
Blocked actions return OWNER_APPROVAL_REQUIRED. See SECURITY.md.
Running locally (Phase 1 — skeleton, working)
# optional: cp .env.example .env (NEVER commit .env)
npm install
npm run build # tsc → dist/
npm run dev # hot-reload dev server (tsx)
# or production-style:
npm start # node dist/server.jsThen:
curl http://localhost:3000/health # {"ok":true,...}
curl -X POST http://localhost:3000/mcp # 501 placeholder (tools land in Phase 2)
# open http://localhost:3000/ in a browser for the private dashboardScripts: npm run build · npm run dev · npm start · npm run typecheck ·
npm test · npm run lint.
Docker (local)
docker compose up --build # serves on http://localhost:3000Auth in v0.1
If BRIDGE_ADMIN_TOKEN is unset, the bridge runs in permissive dev mode
(requests pass, a warning is logged) — convenient for local skeleton work. When the
token is set, private endpoints (/, /mcp) require Authorization: Bearer <token>.
The token must be set before the bridge is ever exposed.
Deploying with Coolify (Phase 5+, not built yet)
See docs/COOLIFY_DEPLOYMENT.md. Deployment is staging only in v0.1 and requires owner approval.
Environment variables
Only these are used. See .env.example for placeholders.
Variable | Required | Notes |
| yes | Strong random token for private endpoints |
| yes | Workspace Claude Code is allowed to operate in |
| yes |
|
| no | e.g. |
| no | SQLite path or Postgres URL |
| if needed | For Claude Code execution |
| if needed | Repo operations |
| if needed | Staging deploy |
Never commit .env. Never log secrets.
Safety warnings
This is private infrastructure. Do not expose it publicly without owner approval.
The MCP endpoint must always be authenticated.
Claude Code execution is confined to
PROJECT_PATH, never runs as root, always times out and is always logged.Wallet keys, seed phrases, and production secrets are never requested, stored, printed, or committed.
Current status
Code-complete & deploy-ready (local). All 8 MCP tools implemented, strict bearer
auth, full MCP JSON-RPC lifecycle, mock + opt-in real Claude CLI runner, run_tests.
typecheck/build/test pass (51/51); Docker image builds and the container passes a
live smoke test. Live deploy + DNS pending owner access.
See DEPLOYMENT_REPORT.md, BUILD_REPORT.md,
TEST_REPORT.md, NEXT_PROMPT_FOR_CHATGPT.md.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/vipallwork/stabledeliver-bridge'
If you have feedback or need assistance with the MCP directory API, please join our Discord server