Loading
Shell scores 70 out of 100 on the Agent Readiness Index
Shell reaches level 1, Tolerated. Web experience is the strongest area at 100 out of 100. Policy and governance is the weakest at 36.
Shell was scanned on October 2, 2026. Its score is 70 out of 100, level 1, Tolerated. Pages load for an agent. Nothing is built for one. To reach level 2, Legible: Publish at least one machine readable layer: llms.txt, structured data or server rendered content.
Website: shell.com
Score by area
| Area | Score | What it asks |
|---|---|---|
| Discoverability | 46 out of 100, worth 15 points | Can an agent find and read your pages? |
| Protocol access | 84 out of 100, worth 20 points | Can an agent connect to you through MCP or an API? |
| Identity and delegation | 68 out of 100, worth 20 points | Can a customer give an agent limited access without sharing a password? |
| Web experience | 100 out of 100, worth 15 points | Does your site work when an agent uses it? |
| Voice and IVR | Not measured yet | What happens when an agent calls your phone line? |
| Policy and governance | 36 out of 100, worth 10 points | Do your terms allow agents that act for customers? |
What is holding Shell back
- Documented delegate and data sharing controls, 4 points lost. No public page on delegate access or connected app controls was found. Fix: Publish a help page on delegate access and add a connected apps screen where customers revoke access.
- llms.txt guide for agents, 3 points lost. No llms.txt file was found at the site root. Fix: Publish /llms.txt with links to product, pricing, support and location pages.
- Structured data on the home page, 3 points lost. No JSON LD structured data was found on the home page. Fix: Add JSON LD for your organization type, Product or Service, Offer and FAQPage on the pages customers ask about most.
- Content available without running scripts, 3 points lost. Almost none of the visible text is in the first HTML response. An agent that does not run scripts sees an empty page. Fix: Render product, pricing and help content on the server so the first response contains the text.
What already works
- MCP server
- OAuth and OpenID metadata
- Sign in page loads for a declared agent in a browser
How Shell compares
The average score for energy is 42.4 out of 100 across 46 organizations. The average across all 1,420 scored organizations is 42.2 out of 100.
Similar organizations
- Schlumberger SLB, 78 out of 100
- Ecobee, 68 out of 100
- Love's Travel Stops, 65 out of 100
- ONEOK, 62 out of 100