# Fumadocs docs and AI agent readiness

How 2 products documented on Fumadocs score on the AI Agent Readiness Test. Average 79.4%, with the five agent surface checks for each.

Docs platform

2 of the 97 products tested serve their documentation on Fumadocs.

Scores run from 78.8% to 80.0%, averaging 79.4%. Every Fumadocs product tested passes llms.txt, llms-full.txt, Markdown mirror and Docs AI. None ships MCP server. The AI Agent Readiness Test scores the documentation, never the platform, so these numbers describe what these 2 teams published rather than what Fumadocs can do.

## Scores on Fumadocs

AI Agent Readiness Score for each product documented on Fumadocs.

Product

Category

Grade

Score

Reading

Surface

llms

full

.md

MCP

AI

[Composio](https://docsforagents.com/reports/composio-docs-ai-agent-readiness/)

[Agent frameworks & memory](https://docsforagents.com/grades/?category=agent-frameworks)

B-

80.0%

24/30

40/50

pass

pass

pass

fail

pass

[Inkeep](https://docsforagents.com/reports/inkeep-docs-ai-agent-readiness/)

[Agent frameworks & memory](https://docsforagents.com/grades/?category=agent-frameworks)

C+

78.8%

23/30

40/50

pass

pass

pass

fail

pass

## Agent surface on Fumadocs

-   **llms.txt** 2 of 2
-   **llms-full.txt** 2 of 2
-   **Markdown mirror** 2 of 2
-   **MCP server** 0 of 2
-   **Docs AI** 2 of 2

Recorded as Fumadocs, Fumadocs on Next.js during testing. A sample of 2 shows what these teams shipped and does not establish a platform default.

[All docs platforms](https://docsforagents.com/platforms/) · [Every score in one table](https://docsforagents.com/grades/)

Put another docs site through the battery.

[Nominate a docs site](https://docsforagents.com/nominate/)

Canonical URL: https://docsforagents.com/platforms/fumadocs-docs-ai-agent-readiness/