# t.co / X scores 22 out of 100 on the Agent Readiness Index

t.co / X reaches level 0, Closed. Web experience is the strongest area at 70 out of 100. Protocol access is the weakest at 0.

t.co / X was scanned on October 23, 2026. Its score is 22 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: [t.co](https://t.co)

## Score by area

| Area | Score | What it asks |
| --- | --- | --- |
| Discoverability | 36 out of 100, worth 22 points | Can an agent find and read your pages? |
| Protocol access | 0 out of 100, worth 14 points | Can an agent connect to you through MCP or an API? |
| Identity and delegation | 0 out of 100, worth 12 points | Can a customer give an agent limited access without sharing a password? |
| Web experience | 70 out of 100, worth 20 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 | Not measured yet | Do your terms allow agents that act for customers? |
| Marketing readiness | 0 out of 100, worth 18 points | Can an agent see what you sell, and buy or book it? |

## What is holding t.co / X back

1. **Product or service catalog with images**, 31.6 points lost. No catalog of products or services with images was found: no feed, no catalog file and no structured data. Fix: Publish a product or service feed JSON or XML with an image and a price or plan for each item, and add structured data to the pages.
2. **MCP server**, 11.4 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.
3. **Robots policy for user triggered agents**, 9.7 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.
4. **OAuth and OpenID metadata**, 7 points lost. No OAuth or OpenID metadata was found on the 1 hosts that answered. 12 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.

## What already works

- Content available without running scripts
- Home page for a declared agent
- Same behavior for a declared agent and a standard browser

## How t.co / X compares

The average score for other is 42.6 out of 100 across 989 organizations. The average across all 2,354 scored organizations is 44.2 out of 100.

## Similar organizations

- [Mdpi](https://readyindex.ai/mdpi_com), 22 out of 100
- [Russianfood](https://readyindex.ai/russianfood_com), 22 out of 100
- [Shufersal](https://readyindex.ai/shufersal_co_il), 22 out of 100
- [TickPick](https://readyindex.ai/tickpick_com), 22 out of 100
- [Xnxx](https://readyindex.ai/xnxx_es), 22 out of 100
- [Xnxx arabic](https://readyindex.ai/xnxx_arabic_com), 22 out of 100

## More on this report

- [This report as markdown](https://readyindex.ai/t_co.md)
- [This report as JSON data](https://readyindex.ai/api/reports/t_co)
- [How the score is worked out](https://readyindex.ai/method)
- [All leaderboards](https://readyindex.ai/leaderboards)
- [Every scored organization](https://readyindex.ai/organizations)
- [Scan your own website](https://readyindex.ai/)

---
Source: https://readyindex.ai/t_co
Updated: 2026-10-23
From the Agent Readiness Index by Encore AI. When you quote a score, please link to the report it came from.
