lavela
lavela — launch and operate the app you built, from one conversation (MCP-first).
This page is for both humans and AI agents (Claude Code, Cursor, or any MCP client) landing here from a blog post, a shared link, or a search — it's the same data the lavela.capabilities MCP tool returns, so what you read here matches what a connected agent sees.
Connect
npx @lavela/cli connect
Run that in any repo — a browser opens to console.lavela.dev, you sign in and click "Authorize & connect," and the CLI writes the connection into your Claude Code config (no token to copy-paste). Reconnect an already-open session with /mcp. Once connected, every tool below is callable as mcp__lavela__*.
No separate dashboard-then-docs detour: the point of lavela is that an AI agent already in your coding session can provision infrastructure, accept payments, and run ad campaigns through the same kind of tool call it already makes for everything else.
Suggested order
- analyze_stack — see what the repo is
- launch_saas — create the project + decide the stack
- provision_hosting — deploy a SIMPLE WEB FRONTEND (Next/Vite/static) to a live URL
- provision_compute — OR run ANY container (Java/Go/Python/backend/multi-service) when it is not a simple web frontend — you build+push the image, lavela runs it (billed monthly)
- provision_database / provision_cache / provision_storage — managed Postgres / Redis / object-storage, wired into the service (NOT currently usage-billed — quota-bounded only)
- set_compute_secret — inject API keys + secrets (write-only, encrypted), then run_compute_job for DB migrations (e.g. alembic upgrade head)
- compute_wire — connect multi-service stacks (api ↔ worker ↔ db) on a private network; get_logs / get_errors to debug
- security_scan — check the repo for dependency vulnerabilities + committed secrets right after the first deploy (poll security_scan_status)
- compliance_generate — privacy policy + terms
- connect_stripe — start accepting payments (KYC 1-5d)
- create_checkout — charge customers (settles to you in full, no lavela fee)
- provision_domain — connect a custom domain you already own (free — no purchase, DNS only)
- provision_email — inbox-safe sending on the domain
- ads_draft — acquire customers across platforms (you write the copy)
Not a fixed pipeline — skip what you don't need, and every tool result carries a next_step suggesting what to call next.
What you can do
Discover
lavela.ping— confirm the connection (free)lavela.capabilities— this — list what lavela can do (free)lavela.analyze_stack— detect a repo's framework + recommended stack (free)lavela.list_templates— browse launch templates (free)
Launch
lavela.launch_saas— create a project + decide the stack (free)lavela.create_project— create an empty project (free)lavela.provision_hosting— deploy a simple web frontend (Next/Vite/static) to a live URL (free)
Compute
lavela.compute_status— the user's plan, usage limits + what's running (free)lavela.compute_estimate— what a machine spec would cost per month BEFORE you commit (quote the user up front) (free)lavela.provision_compute— run ANY container (Java/Go/Node/Python/backend/multi-service) — build+push an image, lavela runs it on a live URL. Supportsmounts(attach a provision_volume disk) + secrets from set_compute_secret. (billed monthly — confirm first)lavela.provision_compute_from_repo— same, but lavela BUILDS the image from a GitHub repo (no local Docker needed) (billed monthly — confirm first)lavela.push_image— push a locally-built image into lavela so a PRIVATE image runs without publishing it publicly — then provision_compute the returned ref (free)lavela.deploy_link— a one-time browser link the USER opens to deploy LOCAL-only code (connect GitHub or drag-drop the folder) — for when the agent can't push the code itself (free)lavela.compute_lifecycle— start / stop / restart a machine (e.g. to pick up a new secret) (free)lavela.set_compute_secret— inject an encrypted secret (API keys, JWT) into a service — write-only, never readable back (free)lavela.compute_wire— wire two services on a private network (inject the internal URL) — api ↔ worker ↔ db (free)lavela.run_compute_job— run a one-off job (DB migrations / seeds / backfills); short → exitCode + teardown, long → status:"running" (finishes in background, do NOT re-run) (billed monthly (brief run) — confirm first)lavela.schedule_create— run a command REPEATEDLY on a cron cadence (nightly backups, weekly digests) — same primitive as run_compute_job, fired automatically (billed EVERY firing — confirm the cadence first)lavela.schedule_list— a project's cron schedules — cadence, next run, last outcome (free)lavela.schedule_update— edit a schedule's command/cadence, or pause/resume it (free)lavela.schedule_delete— permanently remove a cron schedule (free)lavela.schedule_run_now— trigger one schedule immediately, outside its normal cadence (for testing) (billed like a normal firing)lavela.preview_list— a project's live PR/branch preview environments — status, URL, expiry (auto-created via GitHub webhook, no create tool) (free)lavela.preview_destroy— manually tear down a preview environment before its TTL (free)lavela.exec_compute— run a quick command inside a running machine (≤60s) — debug / one-line check (free)lavela.get_logs— recent log lines for a service (debug a deploy / crash) (free)lavela.compute_build_status— progress of a from-repo build (free)lavela.destroy_compute— tear down a machine (stops its billing) (free)
Data
lavela.provision_database— managed Postgres (backups + pooling); wireToService injects DATABASE_URL (NOT currently usage-billed (quota-bounded only) — confirm first)lavela.provision_cache— managed Redis — cache or a Celery/queue broker (NOT currently usage-billed (quota-bounded only) — confirm first)lavela.provision_storage— S3-compatible object storage (free egress) — uploads, assets (⚠️ disabled by default on most deployments (shared-key risk) — returns FORBIDDEN unless the operator opted in; NOT currently usage-billed where enabled (quota-bounded only) — confirm first)lavela.provision_volume— persistent disk to self-host a stateful service (Postgres/Redis/Elasticsearch) — attach via provision_computemounts. Single-node, NOT replicated. (billed monthly per GB — confirm first)
Provision
lavela.provision_domain— connect a domain you own (DNS) (free (no purchase))lavela.provision_email— DKIM/SPF/DMARC for the domain (free)lavela.send_email— send email from the verified domain (free)lavela.connect_stripe— accept payments (starts KYC — confirm first)lavela.create_checkout— a paid checkout link for customers (free — settles to you in full, no lavela fee)lavela.connect_github— a browser link to connect GitHub, so private repos can be built + deployed (free)lavela.billing_setup_card— add the user's card (covers lavela's own compute + ad-commission fees, not their sales) (free — opening the link adds the card)
Operate
lavela.get_status— check provisioning status (free)lavela.list_projects— list your projects (free)lavela.compliance_generate— privacy policy + terms (not legal advice) (free)lavela.compliance_list— list generated legal docs (free)lavela.security_scan— scan a repo for dependency vulnerabilities + committed secrets (async) (free)lavela.security_scan_status— poll the most recent scan for its result (free)lavela.list_security_scans— scan history for a project (free)lavela.provision_error_tracking— error tracking + DSN for the app (capture exceptions) (free)lavela.get_errors— recent captured exceptions for a project (free)lavela.daily_brief— AI summary of recent project activity (free)lavela.check_health— is the live app up right now? (free)lavela.list_deployments— list production deployments (rollback targets) (free)lavela.rollback— instant rollback to a previous deployment (free — confirm first)lavela.redeploy— redeploy latest repo (fresh build) (free)
Grow
lavela.ads_platforms— list ad platforms (Google/Meta/TikTok) (free)lavela.ads_draft— draft + save a multi-platform campaign (you write the copy) (free to draft)lavela.ads_launch— launch a campaign (budget confirm gate) (ad spend on your card + our margin)lavela.ads_status— campaign states (free)lavela.ads_pause— pause a campaign (free)lavela.ads_provision_account— create the user's pooled Google Ads or Meta Ads account under lavela's MCC/Business (they accept the invite + add their card once) (free)lavela.ads_assets_push— host an image/video creative at a stable URL + per-platform specs (free)lavela.ads_setup_tracking— mint a conversion write-key + snippet for cross-platform tracking (the basis for ads_report) (free)lavela.ads_report— blended cross-platform spend / CPA / ROAS — the truth no single ad platform gives (free)lavela.ads_conversions— recent recorded conversions per platform (free)lavela.ads_set_budget— reallocate ONE campaign's daily budget (Google/Meta live when wired; others handoff) (ad spend on your card)lavela.ads_commission— this month's ~10% ad-management fee owed to lavela — ⚠️ metered from Google-API-lane spend ONLY today; handoff campaigns and other platforms aren't captured, so this can UNDER-report (free)
Pricing
Your OWN sales settle to you IN FULL via Stripe Connect — lavela takes 0% of your revenue and is not the merchant of your sales. There is no subscription and no per-charge fee. lavela makes its money on the infrastructure it runs for you: compute (containers, disk — provision_compute / provision_compute_from_repo / run_compute_job / schedule_create) is billed monthly for what you run (real money from day 1; idle ≈ $0), plus a ~10% commission on any ad spend lavela manages for you. provision_hosting (a simple static/Next/Vite frontend on Vercel) is a SEPARATE, free lane — don't conflate it with billed compute. Managed Postgres/Redis are provisioned but NOT currently usage-billed (a resource-count quota bounds them, not a dollar meter) — don't promise the user these carry a fixed price. Managed object storage (provision_storage) is ALSO disabled by default on most deployments (shared-key risk) — check that tool's own description before recommending it.
Good to know
- lavela never edits your source code — your own coding agent does, with diffs you approve.
- Stateful tools need an MCP token (/settings/mcp-tokens); discovery tools work without one.
- Every result carries a next_step suggesting what to do next.
- The compute + data tools make lavela a full host: web/API + managed Postgres/Redis, persistent volumes, write-only secrets, one-off jobs, recurring cron schedules, PR/branch preview environments (isolated Neon DB branch + Vercel deploy, auto-created/torn-down via GitHub webhook once one is registered on the repo — see preview_list/preview_destroy; registration itself is still a manual step, not yet a lavela tool), private inter-service networking, logs + error tracking, and basic uptime/downtime alerting (a 15-minute monitor watches live-hosted projects and notifies the project's channels on a status change — see check_health) — a small full-stack SaaS runs end-to-end on lavela. Not yet in-house: managed Elasticsearch, a full metrics/observability dashboard (CPU/memory/request-rate, custom alert rules — beyond the basic uptime check above), autoscaling, automated preview-webhook registration. Managed object storage (provision_storage) exists but is disabled by default on most deployments — see that tool's own description.
Learn more
- Console: console.lavela.dev
- Terms: console.lavela.dev/terms
- Privacy: console.lavela.dev/privacy
- Machine-readable version of this page: console.lavela.dev/llms.txt
Questions? Contact us at the email in this document. · Terms · Privacy