API Overview

rtrvr.ai exposes three HTTP endpoints for different automation needs: full agent runs, raw page scraping, and browser-as-API for your logged-in Chrome. All share the same authentication and credit system.

Try Playground Get API Key Install Extension

Three Endpoints

POST/execute

Execute API

Full planner + tools engine for end-to-end web automations.

POST/scrape

Scrape API

Raw page text + accessibility tree for your own models.

POST/mcp

Browser as API/MCP

Control your logged-in Chrome via HTTP or MCP.

Authentication

All endpoints use the same API key. Pass it via the Authorization header:

Header

Authorization: Bearer rtrvr_your_api_key

Security: Keep your key server-side. Never embed it in browser code or ship it to clients.

Unified Playground

API Playground

POST /execute

Full planner + tools engine for end-to-end web automations.Full docs →

API Key

Get your API key by signing into rtrvr.ai/cloud, or find it embedded in your MCP URL after installing the Chrome Extension.

Request Body (JSON)

When to Use What

Use Case	Endpoint	Why
End-to-end web automation	`/execute`	Full planner + tools, can write to Sheets/Docs
Feed your own LLM/RAG pipeline	`/scrape`	Infra-only credits, returns raw text + tree
Use logged-in sessions (Gmail, Salesforce, etc.)	`/mcp`	Runs in your Chrome via extension
Bulk data extraction	`/execute`	Use dataInputs + sheets_workflow
Quick page content check	`/scrape`	Cheapest option, predictable schema
MCP client integration (Claude, etc.)	`/mcp`	Direct MCP protocol support

/execute

• Model + infra credits
• Higher latency (LLM calls)
• Full automation capability

/scrape

• Infra-only credits
• Lower latency
• Raw data for your models

/mcp

• Your logged-in browser
• MCP + HTTP support
• Access authenticated sites

Ready to automate?

Join teams using rtrvr.ai to build playful, powerful web automation workflows.