Loading
LinkedIn scores 55 out of 100 on the Agent Readiness Index
LinkedIn reaches level 0, Closed. Web experience is the strongest area at 99 out of 100. Discoverability is the weakest at 36.
LinkedIn was scanned on October 15, 2026. Its score is 55 out of 100, level 0, Closed. Declared agents are blocked from the public website. To reach level 1, Tolerated: The home page must load for a declared agent and robots.txt must not block every agent.
Website: linkedin.com
Score by area
| Area | Score | What it asks |
|---|---|---|
| Discoverability | 36 out of 100, worth 15 points | Can an agent find and read your pages? |
| Protocol access | 36 out of 100, worth 20 points | Can an agent connect to you through MCP or an API? |
| Identity and delegation | 51 out of 100, worth 20 points | Can a customer give an agent limited access without sharing a password? |
| Web experience | 99 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 | 64 out of 100, worth 10 points | Do your terms allow agents that act for customers? |
What is holding LinkedIn back
- MCP server, 8 points lost. No MCP server, server card or registry entry was found for this organization. Fix: Publish a remote MCP server with OAuth. Start with read only tools such as account status, orders or location search, and publish a server card at /.well known/mcp/server card.
- OAuth and OpenID metadata, 5 points lost. No OAuth or OpenID metadata was found on the 7 hosts that answered. 9 other hosts did not answer the scanner and could not be checked. Agents cannot discover where to send a customer to approve access. Fix: Publish /.well known/oauth authorization server and /.well known/oauth protected resource for the customer facing APIs.
- Robots policy for user triggered agents, 4 points lost. robots.txt blocks all 4 user triggered agents from the whole site. Fix: Allow the ChatGPT User, Claude User and Perplexity User agents in robots.txt for public product, pricing and help pages.
- PKCE and client registration, 4 points lost. No authorization server metadata, so PKCE and client registration could not be confirmed. Fix: Require PKCE with S256 and support client ID metadata documents or dynamic client registration for approved agent clients.
What already works
- Passkeys at sign in
- Sign in page loads for a declared agent in a browser
- Content available without running scripts
How LinkedIn compares
The average score for software is 61.4 out of 100 across 124 organizations. The average across all 1,421 scored organizations is 42.2 out of 100.
Similar organizations
- Grammarly, 56 out of 100
- Boston Consulting Group, 55 out of 100
- Cursor, 55 out of 100
- OpenAI, 55 out of 100
- SAIC, 55 out of 100
- Scale AI, 55 out of 100