MCP Integration
Quick summary of Model Context Protocol integration
MCP Integration
The Model Context Protocol (MCP) gives your AI assistant direct access to your data sources (Database, Figma, Codebase).
We have moved the Detailed Configuration Guides to the Available Servers section below. For a step-by-step tutorial on what MCP is, check the Learning Center.
Browse Available Servers
Supabase, Firebase, RevenueCat, Figma configuration
Supported Services
| Service | Feature |
|---|---|
| Supabase | Schema Inspection, SQL Generation |
| Firebase | Firestore Querying, Analytics |
| RevenueCat | Subscription Management |
| Figma | Design-to-Code |
| Context7 | Semantic Codebase Search |
Check the Learning Center for best practices and security.
MCP in the Boilerplate
The boilerplate ships a per-repo .mcp.json so your AI assistant (Claude Code, Cursor, Antigravity) picks up the right servers the moment you open the project, with no global config editing. Two of these servers turn your own app data into context the assistant can read.
.mcp.json only points to servers and reads from environment variables. It never contains secrets: keys stay in your .env and your .gitignored service-account files.
Firebase MCP → your GA4 analytics
The Firebase MCP server is wired to read your Google Analytics 4 data. Once your Firebase project is connected, you can ask your assistant questions about real usage instead of clicking through dashboards:
"How many users completed onboarding last week?" "Which screen has the highest drop-off in the last 7 days?"
See the Firebase MCP guide for the service-account setup and the exact config block.
Wire AI MCP → your onboarding insights
Wire AI runs a hosted MCP server, the same model as Supabase or HeyGen. Nothing runs from your repo: no server to build, no self-host, no local config file. You point your AI assistant at the hosted URL and authenticate with your key.
- Server URL:
https://wireai-mcp.fly.dev/mcp(HTTP transport) - Auth: an
Authorization: Bearer <key>header on every request
Add it to Claude Code with one command:
claude mcp add --transport http wireai https://wireai-mcp.fly.dev/mcp \
--header "Authorization: Bearer <key>"For any other MCP client (Cursor, Codex, and the rest), paste the same URL and bearer header into that client's MCP settings.
Two key scopes. Which tools you get depends on which key you authenticate with:
| Key | What it unlocks |
|---|---|
Tenant wai_ key | Read + loop tools (wireai_get_insights, wireai_submit_learning_report, wireai_mark_learning_applied) plus the no-auth guide/components tools |
| Admin key | Everything above, plus app management (register / update / list) and experiment tools (wireai_get_experiments and the three arm-setters for onboarding / review / questionnaire arms) |
The backend enforces scope per call. Grab your key from the getwireai dashboard: open your app, go to the Set Up tab, copy its key. Read it from your environment; never commit it.
Download insights as .md for your AI
Prefer to hand the data to an assistant that isn't wired to MCP? Wire AI exposes the same insights as a plain markdown file you can download and paste in:
- Via the API:
GET /v1/me/apps/{appId}/insights.mdreturns the analytics as markdown. - Via the getwireai dashboard: a one-click download
insights.mdaction.
The .md format is deliberate: it drops straight into any AI chat as context, so your assistant can reason over real onboarding behaviour when you ask it what to build or change next.