dsh-linkdigest
适用于 DeepSeek Harness 的 LinkDigest：通过内置的 @deepseek-ai/dsh-mcp-client 桥接器挂载远程 LinkDigest MCP（https://linkdigest.dev/mcp），将小红书、抖音、TikTok、YouTube 或 X 链接转换为代理可读取的文本。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:jcaiagent7143-ui/linkdigest-mcp#c095f6f94942e010667c3bf452b218ad1826d476Linkdigest 以 dsh-linkdigest 发布，当前版本为 1.0.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Turn a social media link into text a language model can read — transcript, on-screen text, image descriptions, caption and metadata.
Hosted, remote (streamable HTTP). Nothing to install or run.
Website: linkdigest.dev · Registry: dev.linkdigest/linkdigest
Fetching a social link yourself returns nothing useful. Share URLs are tokenised
(xsec_token, app_code_link), the content lives in video and images rather
than HTML, and the server sends an app-download shell or a login wall instead of
the post.
$ curl -s 'https://xhslink.com/o/1WiQ1QI6Uc0' | grep -o '<title>.*</title>'
<title>小红书</title>
That is the whole page. No caption, no images, no text.
Claude Code
claude mcp add --transport http linkdigest \
https://linkdigest.dev/mcp \
--header "Authorization: Bearer ld_live_..."
Cursor — ~/.cursor/mcp.json
{
"mcpServers": {
"linkdigest": {
"url": "https://linkdigest.dev/mcp",
"headers": { "Authorization": "Bearer ld_live_..." }
}
}
}
A key is issued at linkdigest.dev/app/keys. Three digests are free, no card.
digest_url(url, format, job_id) — only url is required.
| Argument | Notes |
|---|---|
url | The post URL, including any share tokens. |
format | markdown (default, best for reading) or json (structured). |
job_id | Collect a digest already running. Pass this instead of url — re-sending the url would start the work again. |
You do not call it yourself. The tool description tells the agent to reach for it whenever it meets a social link it cannot read, so it happens mid-task without being asked.
A long video may not finish inside one call. When that happens the result names a
job id; call the tool again with that job_id and no url to collect it.
platform, author, title, posted_at, caption, transcript ({t, text}),
ocr_text, images ({description, ocr}), key_points, raw_markdown,
source_url, transcript_source, degraded.
Two are worth knowing about:
transcript_source — native_captions, asr, or none. Captions the
platform already published are exact; speech recognition is not. Treating them
identically eventually quotes a mis-heard number back at someone as fact.degraded — what did not fully work, in plain words. Empty on a clean run.
It exists because a digest once returned a well-formed, completely empty result
during a provider outage and was cached for thirty days.Checked against real posts, not documentation.
| Platform | Status |
|---|---|
| Xiaohongshu 小红书 | Works — image notes and video notes, no login needed |
| Douyin 抖音 | Works — video posts and image notes (图文) |
| TikTok | Works — short links resolve. Rate-limits under load |
| YouTube | Works — native captions where published, otherwise a watched transcript |
| X | Works — posts with video or images |
| Web pages / articles | Works — readable article text, title, author, date |
| Bilibili | Not supported. Returns HTTP 412 to our server's address. Needs a proxy |
| Not verified. Wired, not confirmed end to end | |
| Not supported. Serves no post content to logged-out requests |
The rows that do not work are listed on purpose. Finding out after you have wired something in is worse than knowing now.
Measured, not estimated:
A REST API (POST https://linkdigest.dev/api/v1/digest), a web app, and Apify
Store actors for bulk runs. See linkdigest.dev.