Skip to main content
Connect Claude, Cursor, ChatGPT or Gemini to your Manglai platform and query carbon, water and waste data in natural language.

What Can You Do?

Companies

Query company hierarchy, buildings, departments and annual configuration

Consumptions

List and filter energy consumption records. Get dashboards by category, building and period

Emissions

Calculated emissions by scope, category, building and month. Aggregated CO₂e dashboard

Invoices

Electricity, gas, fuel, water and waste invoices with CO₂e data

Vehicles

Vehicle fleet with engine type, fuel and associated emissions

Employees

Employee list and commuting data

Business Travel

Travel records with transport type and emissions per trip

GLEC Logistics

Logistics service footprint aligned with the GLEC standard

Goals

Reduction targets, tracking tasks and projection scenarios

Reference Data

GHG Protocol categories, emission factors, recommended inputs by country

Available Tools

How It Works

Security

  • Read by default — Most tools are GET-only
  • Confirmed writesupsert_company_building and upsert_vehicle require userConfirmed: true after explicit user approval
  • Token-scoped access — Access is limited to what your token can see
  • No data storage — Data flows through directly, nothing is cached

What is MCP?

The Model Context Protocol connects your AI assistant to Manglai. Server resource: manglai://api/what-is-mcp.

Create or update buildings and vehicles

Updates: the API uses POST upsert (not PATCH). Send the same id and the full body (fetch with get_company_buildings or get_vehicle, merge, then submit). Agent guides: manglai://api/mutations/buildings and manglai://api/mutations/vehicles (include guide and fix).

Architecture

Getting Started

Quickstart

Set up the Manglai MCP in 5 minutes