UsageWall

curl -s https://usagewall.vercel.app/api/mcp \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Settings → Connectors → Add custom connector → pastehttps://usagewall.vercel.app/api/mcp

Six read-only tools, two raw-JSON resources, JSON-RPC 2.0 over Streamable HTTP. Zero dependencies; ~280 LOC; auditable in one sitting.

Tools—list_models,get_model,compare_models,estimate_cost,cheapest_for,list_providers.

Resources—usagewall://pricing/full,usagewall://pricing/<provider>.

Production-grade waitlist landing forusagewall.dev, plus the local proxy prototype. Static HTML + 5 Vercel serverless functions. No build step. No framework.

Both must be ≥32 chars. The handler refuses to sign tokens with shorter secrets.

- A record@→76.76.21.21
- CNAMEwww→cname.vercel-dns.com

To test without Vercel CLI, use the smoke server:

npm run smoke # Hits the handler with stubbed Supabase, prints pass/fail per case.

npm test # unit + E2E (48 + 13 = 61 cases, no network) npm run validate:html # HTML structure + CSP + a11y checks npm run smoke # live HTTP smoke vs handler with stubbed Supabase npm run ci # all of the above

CI runs on every push that touchesusagewall/(see.github/workflows/test.yml).

GO if≥100 emailsand≥1 replyasking "when can I pay?" NO-GO if<30 emailsafter the launch thread.

This isnot*the Baku brand — it's UsageWall, a productbyBaku. Inherits the design DNA (dark warm, editorial serifs, no flashy gradients, generous spacing) but lives independently with its own identity. Footer credits Baku.

- .env,.env.local,.env..local
- .vercel/(project link)
- node_modules/

The CI grep checks for accidental commits ofsk_live_…,re_…,sbp_….

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

An MCP server which brings Jotform to your AI client or LLM

Transform your scattered documentation into AI-ready knowledge that works seamlessly with Claude, Cursor, VS Code, and other AI tools.

Plug your AI agent into OpenCharts—build spreadsheets, boards, music, and automations from Claude Code, Codex, or Cursor without leaving your terminal.

An AI-powered bridge connecting assistants like Claude and ChatGPT to RADAAR for managing posts, inboxes, analytics, and social listening across 20+ channels using natural language.

After Effects MCP is a full-featured automation bridge that connects AI clients (like VS Code, Claude Desktop, and Claude Code) to Adobe After Effects through MCP, enabling scripted control of compositions, layers, effects, keyframes/graph easing, presets, markers, audio levels, waveform analysis, and effect discovery via a live bridge panel.

AI-native workflow orchestration with long-term memory. 100+ integrations through single credit system. 32 MCP tools for building and running intelligent business workflows — lead enrichment, content publishing, company research, media production. Knowledge Graph that learns across executions. Works with Claude, Codex, Cursor, Windsurf.

Project management your AI can actually run — connect Claude, ChatGPT, Cursor & Codex to one board over MCP.