Skip to content

LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server

dev.linkdigest/linkdigestlinkdigest.devstreamable-httpv1.0.13Scanned

Read Douyin, RedNote, Bilibili, Toutiao, Weibo, YouTube, TikTok as text; search RedNote and Douyin

5 tools: 1 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 1 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server can do

The LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server is published by linkdigest.dev, a domain the MCP Registry verified. It has 5 tools. It can create or change data (1 tool: check_balance), but cannot delete data. 4 tools only read.

1 tool reads private data (list_batches); 4 tools bring in text other people can write (digest_url, compare_links, list_batches and 1 more); 2 tools can send data out of your system (digest_url and compare_links). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 4 times since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.0.13.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Changes things 1Claude Code: ask
  • check_balanceHow many credits this API key has left, what each kind of read costs, and where to buy more (links need no sign-in; the credit pack takes Alipay).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How many credits this API key has left, what each kind of read costs, and where to buy more (links need no sign-in; the credit pack takes Alipay). Without a key it returns the prices and how to get a key. Call it before a batch of reads, or when digest_url says credits ran out.

    Annotations the server declares

    • title: Credits left and what a read costs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 4Show 4 read-only tools
  • digest_urlRead what a social media link actually says.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "digest_url" says "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read what a social media link actually says. Works on Xiaohongshu, Douyin, Weibo, Hongguo 红果短剧 drama pages, Toutiao 今日头条 articles and videos, TikTok, YouTube, X, Instagram, Bilibili, podcast episodes (小宇宙, Apple Podcasts) and ordinary web pages. Returns the post's transcript with times, on-screen text, the text in every image, caption and counts, key points each backed by a quote checked against the post (`key_point_support` in json), and a receipt of what was read (`coverage` in json). Facebook and Spotify are not supported. Works without an API key for a first look (a summary, two a day per address); the full output needs a key — see check_balance. If the result names a job id, call again with job_id only. Example: url="https://v.douyin.com/abc/", ask="推荐了什么产品、多少钱?".

    Annotations the server declares

    • title: Read a social media post as text
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • list_batchesThe last batches on this API key, newest first — including the ones the browser extension's “Digest the notes on this page” button started from the user's own Xiaohongshu or Douyin…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_batches" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    • untrusted-inputThe description's first sentence says "browser": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The last batches on this API key, newest first — including the ones the browser extension's “Digest the notes on this page” button started from the user's own Xiaohongshu or Douyin tab. Each line: batch_id, label, created, status done/total, credits, synthesis (ready, pending, failed or none). Pass a batch_id to compare_links to read the comparison. Starts nothing, costs nothing. Needs an API key.

    Annotations the server declares

    • title: This account's last batches
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

8 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__linkdigest__list_batches"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:52 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://linkdigest.dev/.well-known/oauth-protected-resource/mcp
Authorization servers
https://linkdigest.dev
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://linkdigest.dev/mcp: tools/list returned 5 tools to an anonymous client, including check_balance (write)

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • RFC 9728 protected resource metadata: https://linkdigest.dev/.well-known/oauth-protected-resource to https://linkdigest.dev/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://linkdigest.dev
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to yes

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff
  2. Tools2 changed.~2 changedView diff
  3. PostureRemote posture changed. RFC 9728 protected resource metadata: https://linkdigest.dev/.well-known/oauth-protected-resource -> https://linkdigest.dev/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://linkdigest.…View diff
    • RFC 9728 protected resource metadata: https://linkdigest.dev/.well-known/oauth-protected-resource to https://linkdigest.dev/.well-known/oauth-protected-resource/mcp
    • Authorization servers: none to https://linkdigest.dev
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to yes
  4. Tools3 changed.~3 changedView diff
  5. Tools1 changed.~1 changedView diff

Install

Pinned to version 1.0.13. Values in angle brackets are yours to fill in.

claude mcp add --transport http linkdigest https://linkdigest.dev/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http linkdigest https://linkdigest.dev/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__linkdigest__list_batches",
      "mcp__linkdigest__search_links"
    ],
    "ask": [
      "mcp__linkdigest__digest_url",
      "mcp__linkdigest__compare_links",
      "mcp__linkdigest__check_balance"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as linkdigest. Review it before you use it.

Capability tags behind 4 rules
  • mcp__linkdigest__digest_url untrusted-input, outbound
  • mcp__linkdigest__compare_links untrusted-input, outbound
  • mcp__linkdigest__list_batches private-data, untrusted-input
  • mcp__linkdigest__search_links untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/dev.linkdigest/linkdigest/verify?hash=c2061fcacd1ee039d66d2f225d455a2ee0b1846913d53003c0c728f9f45c56ac" | jq -e '.changed == false'

Pinned hash c2061fcacd1e, from Nov 20, 2026, 08:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/dev.linkdigest/linkdigest/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for dev.linkdigest/linkdigest
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.linkdigest/linkdigest.svg)](https://radar.anlyon.com/servers/dev.linkdigest/linkdigest)

Source: MCP Registry · repository. Synced Nov 20, 2026, 08:17 UTC.

LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server have?

5 tools: 1 write, 4 read. check_balance, digest_url, compare_links, list_batches and search_links.

Does the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): digest_url and compare_links.

Has the LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text MCP server changed its tools?

Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.