loading…
Search for a command to run...
loading…
We built a hosted MCP server that gives AI agents two capabilities through a single connection: 1. img-forge — Image generation across 5 quality tiers (SDXL Lig
We built a hosted MCP server that gives AI agents two capabilities through a single connection: 1. img-forge — Image generation across 5 quality tiers (SDXL Lightning to Gemini 3.1 Flash). One tool call, 5-30 seconds, done. 2. Stackbilder — Full-stack architecture scaffolding. Describe a product, get a 6-mode pipeline (Product → UX → Risk → Architect → TDD → Sprint)
Two products. One MCP connection. Image generated by img-forge (ultra tier).
MCP Registry: dev.stackbilt.mcp/gateway — published on the Official MCP Registry
OAuth-authenticated Model Context Protocol (MCP) gateway for Stackbilt platform services. Built as a Cloudflare Worker using @cloudflare/workers-oauth-provider.
A single MCP endpoint (mcp.stackbilt.dev/mcp) that routes tool calls to multiple backend product workers:
| Backend | Tools | Description |
|---|---|---|
| TarotScript | scaffold_create, scaffold_classify, scaffold_publish, scaffold_deploy, scaffold_import, scaffold_status |
Deterministic project scaffolding, n8n workflow import, GitHub publishing, CF deployment |
| img-forge | image_generate, image_list_models, image_check_job |
AI image generation (5 quality tiers) |
| Stackbilder (TarotScript backend) | flow_create, flow_status, flow_summary, flow_quality, flow_governance, flow_advance, flow_recover |
DEPRECATED — Architecture flow orchestration (migrating to scaffold_*) |
You: "Build a restaurant menu API with D1 storage"
↓
scaffold_create → structured facts + 9 deployable project files
↓
scaffold_publish → GitHub repo with atomic initial commit
↓
git clone → npm install → npx wrangler deploy → live Worker
Zero LLM calls for file generation. ~20ms for structure, ~2s with oracle prose. 21x faster than flow_create.
RATELIMIT_KV (free=20/min, hobby=60, pro=300, enterprise=1000); 429 with Retry-After and X-RateLimit-* headersedge-auth before dispatch and committed/refunded on outcome; image_generate cost scales with quality_tier (1×/1×/3×/5×/8× for draft/standard/premium/ultra/ultra_plus)tools/list is filtered by token scopes; tools/call requires the generate scope for mutating tools; expensive image_generate quality tiers (premium and above) are gated to Pro+ plansREAD_ONLY, LOCAL_MUTATION, EXTERNAL_MUTATION); structured audit logging with secret redaction; HMAC-signed identity tokensPUBLIC_SIGNUPS_ENABLED flag to control public accessnpm i -g wrangler)npm install
npm run dev
npm test
npm run deploy
Deploys to the mcp.stackbilt.dev custom domain via Cloudflare Workers.
| Name | Type | Description |
|---|---|---|
SERVICE_BINDING_SECRET |
Secret | HMAC-SHA256 key for signing identity tokens |
API_BASE_URL |
Variable | Base URL for OAuth redirects (e.g. https://mcp.stackbilt.dev) |
AUTH_SERVICE |
Service Binding | RPC to edge-auth worker (AuthEntrypoint) |
STACKBILDER |
Service Binding | Route to edge-stack-architect-v2 worker |
IMG_FORGE |
Service Binding | Route to img-forge-mcp worker |
OAUTH_KV |
KV Namespace | Stores social OAuth state (5-min TTL entries) and MCP sessions |
RATELIMIT_KV |
KV Namespace | Per-tenant fixed-window rate-limit counters (60s TTL) |
PLATFORM_EVENTS_QUEUE |
Queue | Audit event pipeline (stackbilt-user-events) |
MCP_REGISTRY_AUTH |
Variable | MCP Registry domain verification string (served at /.well-known/mcp-registry-auth) |
Set secrets with:
wrangler secret put SERVICE_BINDING_SECRET
src/
index.ts # Entry point — OAuthProvider setup, CORS, health check, MCP Registry well-known
gateway.ts # MCP JSON-RPC transport, session management, tool dispatch
oauth-handler.ts # OAuth 2.1 flows: login, signup, social SSO, consent
tool-registry.ts # Tool catalog aggregation, namespacing, schema validation
audit.ts # Structured audit logging, secret redaction, trace IDs
auth.ts # Bearer token extraction & validation
route-table.ts # Static routing table, tool-to-backend mapping, risk levels
types.ts # Type definitions, RiskLevel enum, interfaces
test/
audit.test.ts
auth.test.ts
gateway.test.ts
oauth-handler.test.ts
route-table.test.ts
tool-registry.test.ts
docs/
user-guide.md # End-user guide: account creation, client setup, tool usage
api-reference.md # MCP tool surface, authentication flow, tool routing
architecture.md # System design, security model, request flow
122 tests across 6 test files covering:
initialize, tools/list, tools/call, SSE streaming, error handlingnpm test # single run
npm run test:watch # watch mode
MIT — see LICENSE
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"stackbilt": {
"command": "npx",
"args": []
}
}
}Transcripts, channel stats, search
AI image generation using various models.
Unified GPU inference API with 30 AI services (LLM, image gen, video, TTS, whisper, embeddings, reranking, OCR) as MCP tools. Pay-per-use via x402 USDC or API k
A powerful image generation tool using Google's Imagen 3.0 API through MCP. Generate high-quality images from text prompts with advanced photography, artistic,