Loading
Intercom scores 91 out of 100 on the Agent Readiness Index
Intercom reaches level 4, Trusted. Discoverability is the strongest area at 98 out of 100. Protocol access is the weakest at 84.
Intercom was scanned on October 3, 2026. Its score is 91 out of 100, level 4, Trusted. A customer can authorize an agent with limited, revocable access. To reach level 5, Native: Support agents on every channel: passkeys, a high assurance profile and a voice line scoring 70 or more.
Website: intercom.com
Score by area
| Area | Score | What it asks |
|---|---|---|
| Discoverability | 98 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 | 91 out of 100, worth 20 points | Can a customer give an agent limited access without sharing a password? |
| Web experience | 90 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 | 98 out of 100, worth 10 points | Do your terms allow agents that act for customers? |
What is holding Intercom back
- Passkeys at sign in, 4 points lost. No passkey signal was found on the sign in page or in the published pages read. A prompt that starts only after a person types is not visible to the scan. Fix: Offer passkeys with conditional UI on the sign in page and for step up approvals.
- Browser tools exposed to agents, 3 points lost. The sign in and home pages register no browser tools for agents. Fix: Register tools for safe tasks such as location search and price lookup with navigator.modelContext.
- Sign in form structure and autofill hints, 2.7 points lost. 67 percent of 3 fields have labels and 0 percent set autocomplete hints. Fix: Label every field and set autocomplete values for the username, the current password and the one time code.
- Robots policy for user triggered agents, 2 points lost. Some user triggered agents are restricted in robots.txt. Fix: Allow the ChatGPT User, Claude User and Perplexity User agents in robots.txt for public product, pricing and help pages.
What already works
- MCP server
- OAuth and OpenID metadata
- PKCE and client registration
How Intercom compares
The average score for software is 61.4 out of 100 across 124 organizations. The average across all 1,420 scored organizations is 42.2 out of 100.