Which AI agents send Accept: text/Markdown?
This article lists AI agents that currently support or partially support sending the Accept: text/markdown header in HTTP requests, and provides methods to verify them. As of May 2026, only Claude Code, Cursor, OpenClaw, OpenCode, and Codex CLI (partial) support this feature, while other mainstream agents like ChatGPT, Claude.ai, and Copilot only fetch HTML.
Status
AI agent support matrix.
Which AI agents send Accept: text/markdown (or otherwise advertise a Markdown preference) when their built-in browse or fetch tools hit a URL.
Agent
Status
Mechanism
Verified
Claude Code Anthropic
Supports
Accept: text/markdown, text/html, */*
RFC 7763 RFC 9110
2025-11-13
Cursor Anysphere
Supports
Accept: text/markdown, text/plain;q=0.9, */*;q=0.8
RFC 7763 RFC 9110
2026-04-18
OpenClaw OpenClaw
Supports
Accept: text/markdown, text/html;q=0.9, */*;q=0.1
RFC 7763 RFC 9110
2026-05-04
OpenCode SST
Supports
Accept: text/markdown;q=1.0, text/x-markdown;q=0.9, text/plain;q=0.8, text/html;q=0.7, */*;q=0.1
RFC 7763 RFC 9110
2026-05-04
Codex CLI OpenAI
Partial
Follows
RFC 7763 RFC 8288
2026-04-18
Aider Aider
No
Fetches only HTML
2026-05-09
ChatGPT (browse) OpenAI
No
Fetches only HTML
2026-04-18
Claude.ai (web app) Anthropic
No
Fetches only HTML
2026-04-18
Cline Cline
No
Fetches only HTML
2026-05-09
Copilot Chat (VS Code) GitHub / Microsoft
No
Fetches only HTML
2026-04-18
Copilot CLI GitHub / Microsoft
No
Fetches only HTML
2026-04-18
Devin Cognition
No
Fetches only HTML
2026-05-09
Gemini (web app) Google
No
Fetches only HTML
2026-04-18
Gemini CLI Google
No
Fetches only HTML
2026-04-18
Grok xAI
No
Fetches only HTML
2026-04-18
Microsoft Copilot Microsoft
No
Fetches only HTML
2026-05-09
Perplexity Perplexity
No
Fetches only HTML
2026-04-18
v0 Vercel
No
Fetches only HTML
2026-05-09
Windsurf Cognition
No
Fetches only HTML
2026-05-09
Zed Zed Industries
No
Fetches only HTML
2026-05-09
Last updated 2026-05-09.
Verify an AI agent yourself
We test the matrix ourselves, but AI agent behavior shifts across versions, plans, and newly-added tools. You can corroborate any row — or catch a regression — by triggering an agent against your own server and reading the request from your access logs.
- Capture the Accept header in your logs
Default log formats usually drop it. Add it once:
log_format with_accept '$remote_addr - $remote_user [$time_local] ' '"$request" $status $body_bytes_sent ' '"$http_referer" "$http_user_agent" ' 'accept="$http_accept"'; access_log /var/log/nginx/access.log with_accept;
LogFormat "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" accept=\"%{Accept}i\"" with_accept
example.com { log { output file /var/log/caddy/access.log format json } }
JSON access logs include request.headers.Accept by default.
- Trigger a known AI agent against a specific URL
Pick a URL on your site — ideally a unique or freshly-published one so the request isn't masked by background traffic. Then ask the agent to fetch or summarize it:
ChatGPT — "Summarize https://yoursite.com/article-xyz" (with the browse tool enabled)
Claude — "What does https://yoursite.com/article-xyz say?" (requires web_fetch / web_search)
Perplexity — paste the URL directly into a query
…and so on for whichever agent you're testing.
- Report what you saw
Grep for the URL in your access log and send the line(s) to feedback, along with the agent you used and the prompt you sent. The accept= field tells us whether text/markdown was advertised.