MediaClawMediaClaw
RedNote, Douyin & TikTok MCP

RedNote, Douyin and TikTok MCP: let your AI agent collect social data through your own browser

The MediaClaw MCP server is a standard MCP (STDIO) server with 40+ tools. It collects RedNote (Xiaohongshu), Douyin and TikTok posts, videos, comments, profiles and search results, then extracts video transcripts and image text. Every page visit goes through the MediaClaw extension in your own browser, using the account you are already logged into, so the agent never sees your cookies. Eight agent hosts are supported today, including Codex, Claude Code and Cursor.

What tools the MCP server provides

40+ tools in five groups. The agent reuses data you have already collected before it starts anything new.

Collect

Start from a link, keyword, profile or search and get the raw data.

  • Post and video details, batch link collection
  • Comments and replies
  • Creator profiles and their posts
  • Keyword search results and account scans

Extract

Turn videos and images into text the agent can read.

  • Timestamped video transcripts (confirmed before running)
  • Text extracted from post images
  • Post body and engagement metrics

Research

Ready-made research actions instead of prompts written from scratch.

  • Keyword topics and long-tail expansion
  • Benchmark account discovery and hit analysis
  • Single-post breakdowns

Read saved data

Anything already stored in the extension is queryable.

  • Local collection records and data pool queries
  • Saved analyses and style profiles
  • Task progress and connection status

Comment outreach

Message users picked from collected comments, only after you confirm the final send.

  • Prepare recipients and message copy
  • Set send intervals and a daily cap
  • Stop remaining sends at any time

Which agents are supported

All three hosts use the same package, the same MCP tools and the same content research skill. Only installation and updates differ.

Codex

InstallPaste the install prompt from the extension; Codex installs everything
Auto-update

Claude Code

InstallSame as Codex; the agent installs it with Claude Code's plugin commands, then you open a new session
Auto-update

Cursor

InstallPrompt-driven; the agent adds MediaClaw to Cursor's MCP config, shared by the editor and cursor-agent CLI
Auto-update

Grok Build

InstallPrompt-driven; the agent adds a local MCP connector to the Grok config
Auto-update

Grok Bot (cloud computer)

InstallThe extension and agent both run on Grok's cloud computer; it approves pairing for you, you only log in to the platform
Auto-update

DeepSeek Harness

InstallPrompt-driven; the agent adds a stdio connection to the current profile
Auto-update

MediaClaw MCP vs. open-source RedNote MCP vs. writing your own scraper

Each approach fits a different job. This table only covers getting the data, based on each project's public documentation.

Platforms

MediaClaw MCPRedNote, Douyin, TikTok
Open-source xiaohongshu-mcpRedNote
Own scraper / MediaCrawler etc.Depends; MediaCrawler covers RedNote, Douyin, Kuaishou, Bilibili and more

Login

MediaClaw MCPYour everyday Chrome session; the agent never gets cookies
Open-source xiaohongshu-mcpScan a QR code in its own headless browser; cookies saved locally
Own scraper / MediaCrawler etc.QR code, cookie or phone login saved by the script

Setup

MediaClaw MCPBrowser extension plus one prompt to your agent
Open-source xiaohongshu-mcpDownload a binary or run Docker, then configure the MCP client
Own scraper / MediaCrawler etc.Python environment, Playwright and other dependencies; coding required

Publish posts / like

MediaClaw MCPNo, collection, extraction and analysis only
Open-source xiaohongshu-mcpYes, publishes image and video posts, comments and likes
Own scraper / MediaCrawler etc.Usually no

Transcripts and analysis methods

MediaClaw MCPBuilt-in video transcripts, image text extraction and 12 research methods
Open-source xiaohongshu-mcpNot included
Own scraper / MediaCrawler etc.Not included; wire up your own

Cost

MediaClaw MCPFree extension; agent mode needs a membership, transcripts use credits
Open-source xiaohongshu-mcpFree and open source (Apache-2.0)
Own scraper / MediaCrawler etc.MediaCrawler states learning and research use only; a paid Pro edition exists

Five things the agent must ask you first

Approving the pairing only lets the agent connect. It does not approve every future collection.

Collect an account

What you see firstA plan: target, fields, scope, batches and risk level
After you confirmRuns only the batches in the plan

Video transcripts

What you see firstWhich videos it will transcribe and how long each one is
After you confirmExtraction starts; items already extracted are not extracted again

Batch detail fill

What you see firstThe scope to fill
After you confirmOpens detail pages to collect

Delete data

What you see firstImpact: how many records, comments and transcripts
After you confirmDeletes

Comment outreach

What you see firstFull recipient list, sending account and message
After you confirmSends one by one

FAQ

Give your agent real RedNote, Douyin and TikTok data

Install the free extension, send the install prompt to your agent, and it does the rest.

Updated