mcpField
T
TinyScale

TinyScale

Local
tinyscale.ioDeveloper Tools0Updated 3w ago

About TinyScale

TinyScale provides coding agents with SaaS building blocks such as waitlists, feedback widgets, and changelogs, and lets them verify integrations. Projects can be previewed without signing up or paying, then claimed and continued on the Free plan.

Key features

  1. 01Set up waitlists and feedback widgets
  2. 02Publish changelogs with RSS/JSON feeds
  3. 03Check deployed pages in a browser
  4. 04Configure onboarding checklists and CSV imports
  5. 05Capture page demos and report AI descriptions
  6. 06Verify integrations with real results

Use cases

  1. 01Add a waitlist for a product launch
  2. 02Add feedback and changelog features to an app
  3. 03Check that a deployed page looks as expected
  4. 04Import and validate approved CSV data

MCP support

The local MCP server runs in the project directory, allowing coding agents to configure TinyScale products and verify integrations. Credentials are stored in the Git-ignored `.tinyscale/` directory.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sanv725-tinyscale-agent": {
"command": "npx",
"args": [
"-y",
"tinyscale"
]
}
}
}
Run commandnpx -y tinyscale

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmtinyscale0.10.0

Tools

42

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
namestringYesHuman-readable project name
productsarrayNoOptional products to enable in addition to TinyFeedback and TinyCheck

Details

From the project README

TinyScale

Small SaaS building blocks your coding agent can set up, verify, and hand to you.

Ask your agent to "add a launch waitlist" or "add a feedback widget and a changelog". It creates a TinyScale project with no account and no card, wires the embed into your app, proves it works with a real result, then opens a claim page so you keep it on the Free plan.

ProductWhat you get
TinyWaitlistLaunch waitlist with explicit consent, email confirmation, unsubscribe and export
TinyFeedbackAnonymous plain-text feedback widget, no user accounts needed
TinyChangelogRelease notes you approve, published as a hosted page, RSS/JSON feed and embed
TinyCheckBrowser check that a deployed page really shows what you expect
TinyActivateOnboarding checklist that completes when your backend confirms the work
TinyImportCSV upload, column mapping and validation; your backend pulls approved rows
TinyDemoCaptured walkthrough of a page you own, reviewed before publishing
TinyCiteReport on how AI answers describe your product, with suggested page fixes

Use it from a coding agent (MCP)

Add the local MCP server to your agent. It runs in your project directory and keeps credentials in .tinyscale/ (git-ignored, never returned to the model).

Claude Code

claude mcp add tinyscale -- npx -y tinyscale mcp

Or install the plugin, which adds the MCP server plus a skill that teaches Claude the setup flow:

/plugin marketplace add sanv725/tinyscale-agent
/plugin install tinyscale@tinyscale

Cursor, Windsurf, VS Code, Codex and other MCP clients

{
  "mcpServers": {
    "tinyscale": { "command": "npx", "args": ["-y", "tinyscale", "mcp"] }
  }
}

Then ask: "Use TinyScale to add a launch waitlist to this app and verify it works."

Use it from the command line

Requires Node.js 20 or later.

npx tinyscale workspace discover                      # products and preview limits
npx tinyscale workspace create --name "My app" --products tinywaitlist,tinychangelog
npx tinyscale waitlist create --configuration-json '{...}'
npx tinyscale workspace claim                          # human claims the project, no payment
npx tinyscale --help

Each product has an exact agent guide: agent.md · waitlist · changelog · activate · import · demo · cite

How it works

  1. Preview — the agent creates a project that lasts 72 hours. No sign-up, no card. Limits are small and hard-stop; nothing is charged.
  2. Verify — the agent proves the integration with a real result: a feedback submission ID, a synthetic waitlist signup, a passing browser check with a receipt.
  3. Claim — you open the claim page, sign in, and the same project, IDs and embeds continue on Free. Public-facing actions (accepting real emails, publishing release notes) need your approval.

Security

  • Credentials live only in .tinyscale/agent-state.json (mode 0600, git-ignored). Tool results never include them or the claim link.
  • The CLI only talks to https://api.tinyscale.io (plain HTTP only for localhost development).
  • Widgets only run on exact HTTPS origins you configure; browser checks require proof you own the origin.

Links

tinyscale.io · Products · Guides · Issues

MIT licensed client. The hosted service has its own terms at tinyscale.io.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.