New: Automated Design is live

Your Wells, Inside Any Agent

ChatGPT, Claude, Gemini, or any MCP client calls hosted tools on your rod-lift wells, rank gearbox loads, diagnose wells, read dyno cards. Same credential and scopes as the REST API.

ChatGPT
MCP What This Surface Is

Tools Your Agents Call on Your Wells

Model Context Protocol turns an AI client into a caller on your PetroBench org. The client asks in plain language. The server returns scoped tool results from the live wells.

A Hosted Tool Server

MCP is how agents discover and call tools. PetroBench hosts the server: Claude, ChatGPT, Gemini, Grok, or any MCP-compatible tool connects to one URL.

Your Wells, Not a Demo Sandbox

Agents rank wells, diagnose loads, read dyno cards, and look up equipment on the same rod-lift records your engineers already use.

Same Token as the REST API

One scoped Bearer credential. Same org boundary and abilities as HTTP. No second identity store for agents.

Setup Connect a Client

Connect Your AI in Three Steps

Nothing to install. Works with Claude, ChatGPT, Gemini, Grok, and more.

  1. Step 1

    Create an Access Key

    In Settings, pick what the key can do. Revoke it any time.

  2. Step 2

    Add PetroBench to Your AI

    Paste the PetroBench link and key into your AI app.

  3. Step 3

    Ask About Your Wells

    Ask in plain words. Changes wait for engineer signoff.

  • Claude
  • ChatGPT
  • Gemini
  • Grok
Open the setup guide
Capabilities On Your Wells

What Your Agents Can Do

Real PetroBench operations, called with the same scoped permissions.

Wells

Find the Right Wells

Search, rank, and flag data gaps across your wells.

  • Search & rank
  • Production
  • Data gaps
Compute

Run Sims & Diagnose

Run and compare simulations on the same engine.

  • Simulations
  • Diagnostics
  • Compare
Catalogs

Look Up Equipment

Pull units and rods from your design catalogs.

  • Pumping units
  • Rod strings
  • Installed gear
Account

Stay Inside Limits

Agents stay paced within your org limits.

  • Usage
  • Contacts
  • Account
Full MCP reference
Surfaces Same Engine

One Engine. Three Surfaces

One credential and one set of scopes. Pick the surface that fits how your team works.

Add the MCP Server to Your Client

Open the docs, paste the hosted URL, and ask on your wells from Claude, ChatGPT, Gemini, or any MCP-compatible tool. Same credential and scopes as REST.