Skip to main content
Glama

Second Take

Review a booking. Approve the changes. Recover when something goes wrong.

Second Take is a reservation workspace built around explicit approval and recoverable actions. It checks saved results before retrying interrupted requests and protects changes made by the user.

Usage · Development · Architecture · MCP reference

What it does

  • Books workshop places, equipment, and a calendar event as one reviewed plan.

  • Supports restaurant, appointment, and event reservation flows.

  • Lets users change or cancel individual parts of a plan.

  • Reconciles missing confirmations without duplicating completed actions.

  • Keeps an activity record with downloadable receipts and calendar snapshots.

This is a software-only Alexa+ simulation. Providers are simulated, conversation uses a guided parser, and no real business is contacted.

Related MCP server: Aura+

Run locally

Requires Node.js 24 and pnpm 11.25.0. No API key is needed.

git clone https://github.com/ArhamChoudhary-ui/Second-Take.git
cd Second-Take
corepack enable
corepack pnpm install --frozen-lockfile
corepack pnpm build
corepack pnpm db:local
corepack pnpm start -- --port 3000

Open localhost:3000 and try:

Book a restaurant in Jaipur tomorrow at 7 pm for 2 people.

Visit /demo to explore missing confirmations, protected user edits, and partial cancellations.

Codebase

Folder

Responsibility

src/

Application, components, booking logic, database schema and migrations

config/

Hosting, linting, and database configuration

tests/

Unit tests, integration checks, and shared test helpers

tooling/

Build, runtime, setup, and release utilities

public/

Static assets

docs/

Guides, technical references, and submission materials

React and TypeScript run on Vinext, Cloudflare Workers, and D1. Booking tools use MCP Streamable HTTP. The @/ alias points to src/.

Verification

corepack pnpm typecheck
corepack pnpm test
corepack pnpm build
corepack pnpm verify:worker

The suite covers approvals, duplicate prevention, recovery, conflicts, and session isolation. See the test report for coverage and remaining gaps.

Project information

Contributing · Changelog · Submission materials · Build provenance

Licensed under MIT. Third-party notices are included with their source files.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A full-stack travel booking MCP server that enables AI clients to search flights, make reservations, cancel bookings, and manage persistent state across sessions.
      9
      14 npm
      5
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that enables Alexa+ to autonomously orchestrate multi-step household tasks by decomposing goals into parallel tool calls — cross-session memory and dietary/allergy auditing, culinary planning with wine pairings, Amazon Fresh cart assembly with human-in-the-loop purchase approval, smart-home ambiance and climate control, and calendar scheduling. It pairs AWS Bedrock multi-agent reasoning with Streamable HTTP transport and interactive generative UI cards, carousels, and live IoT sliders.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables users to run a simulated Alexa+ conversation that checks incident status, plans missing evidence, prepares and confirms bounded AWS recovery repairs, applies approved fixes, and reports verified signed evidence. It also provides read-only proof-frontier and acquisition-planning tools while enforcing confirmation and verification gates.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables a simulated Alexa+ care companion to capture daily check-ins, recall longitudinal care-journal history, assess risk, create local family-inbox cards, schedule follow-ups, and produce weekly digests through MCP tools.
      MIT