wechat-channels-mcp
微信视频号 MCP / WeChat Channels MCP by SocialDataX for hot search, video search, details, comments, comment replies, user profiles, user videos, and transcript.
Documentation
微信视频号与公众号 MCP | WeChat Channels and Official Account MCP
This public repository provides public connection docs and MCP metadata for a hosted 微信视频号与公众号 MCP / WeChat Channels and Official Account MCP service by SocialDataX.
If you are looking for a WeChat Channels MCP, 微信视频号 MCP, or 微信公众号文章 MCP for social media research workflows, this repository includes:
- public MCP metadata and client configuration examples
- the hosted `streamable-http` endpoint for clients that support remote MCP
- an `mcp-remote` fallback example for command/stdio-only MCP clients
The business implementation is privately hosted. This repository exposes only the public connection surface for social media content intelligence workflows.
Search Aliases
Common search phrases for this MCP service:
- `微信视频号 MCP`
- `视频号 MCP`
- `视频号 数据 MCP`
- `视频号 热榜 MCP`
- `视频号 评论 MCP`
- `视频号 用户 MCP`
- `微信公众号文章 MCP`
- `公众号文章详情 MCP`
- `WeChat Channels MCP`
- `WeChat Channels data MCP`
- `WeChat Official Account MCP`
- `WeChat Channels video research MCP`
- `WeChat Channels comments MCP`
- `WeChat MCP`
- `微信 MCP`
Service
- Hosted MCP endpoint: `https://mcp.socialdatax.com/wechat/mcp`
- Hosted transport: `streamable-http`
- Authentication: `Authorization: Bearer `
- Product: `SocialDataX` / `社媒数据助手`
- Website and API Key access:
- Registry name: `com.52choujiang/wechat-channels-insights`
- Future registry name: `com.socialdatax/wechat-channels-insights`
- Current public capability version: `0.1.2`
Platform MCP
Use the hosted `streamable-http` endpoint directly from clients that support authenticated remote MCP. For clients that only support command/stdio MCP servers, use `mcp-remote` as a local compatibility proxy.
Workflow Scope
This MCP service is designed for social media content intelligence workflows. It does not provide account login, posting, editing, liking, commenting, forwarding, or other account actions.
Supported workflows include:
- Query the current API Key account's SocialDataX points balance.
- Read the WeChat Channels / 微信视频号 hot search list.
- Fetch WeChat Official Account / 微信公众号 article details and body text from an article link or share text.
- Search WeChat Channels videos by keyword with optional paging and filters.
- Resolve a WeChat Channels video or image-post link or share text into structured work details.
- Read video details when the caller already has an `encrypted_object_id`.
- Fetch paginated first-level comments for comment analysis.
- Fetch paginated replies under a first-level comment.
- Read user profile data when the caller already has a `v2_...@finder` user_id.
- Resolve a video or image-post link or share text into its creator profile data.
- Fetch user-posted work lists, including videos and image posts, from a work link/share text or a `v2_...@finder` user_id.
- Submit a video speech-to-text transcript task; the submit call may wait up to 240 seconds, and unfinished jobs should continue polling the same `job_id` until terminal.
Tools
| Tool | Public purpose |
|---|---|
| `socialdatax_get_points_balance` | Query the current API Key account's SocialDataX points balance. |
| `wechat_get_hot_search_list` | Get the current WeChat Channels / 微信视频号 hot search list. |
| `wechat_get_mp_article_detail_by_url` | Fetch WeChat Official Account / 微信公众号 article detail and body text from an article link or share text. |
| `wechat_search_videos` | Search WeChat Channels videos by search term. Use this tool when the user needs videos found by a search term; when a video or image-post link is available, use the detail tool; when a video link is available and comments are needed, use the comment tool; when a video link or `encrypted_object_id` is available and a transcript is needed, use the speech-to-text tool. Supports `page_token` continuation. |
| `wechat_get_video_detail_by_encrypted_object_id` | Fetch structured video details when the caller already has an `encrypted_object_id`. |
| `wechat_get_video_detail_by_url` | Resolve a WeChat Channels video or image-post link or share text into structured work details. |
| `wechat_get_video_comments_by_object_id` | Fetch paginated first-level comments when the caller already has the same video's `object_id` and `object_nonce_id`. |
| `wechat_get_video_comments_by_url` | Fetch paginated first-level comments directly from a WeChat Channels video link or share text. |
| `wechat_get_video_comment_replies_by_comment_id` | Fetch paginated replies under a first-level comment using the same video's `object_id` and `object_nonce_id` plus the first-level `comment_id`. |
| `wechat_get_user_info_by_user_id` | Fetch user profile data when the caller already has a `v2_...@finder` user_id. |
| `wechat_get_user_info_by_url` | Resolve a WeChat Channels video or image-post link or share text into its creator profile data. |
| `wechat_get_user_posted_videos_by_user_id` | Fetch a paginated list of videos and image posts published by a user when the caller already has a `v2_...@finder` user_id. |
| `wechat_get_user_posted_videos_by_url` | Fetch a paginated list of videos and image posts published by a user from a work link or share text. |
| `wechat_submit_video_speech_text_by_video_url` | Submit a video speech-to-text transcript task from a video link or share text. The submit call may wait up to 240 seconds; if unfinished, continue polling the same `job_id` until terminal. |
| `wechat_submit_video_speech_text_by_encrypted_object_id` | Submit a video speech-to-text transcript task from an `encrypted_object_id`. The submit call may wait up to 240 seconds; if unfinished, continue polling the same `job_id` until terminal. |
| `wechat_get_video_speech_text_job` | Continue checking a video speech-to-text transcript job using a valid `job_id` supplied by the user, or a `job_id` returned by a submit tool, without creating a new task; each call waits up to 240 seconds. If unfinished, continue querying the same `job_id` until terminal. This v1 surface returns transcript plus content context, not summary. |
Quick Start
For clients that support authenticated `streamable-http`, use the hosted endpoint directly:
{
"mcpServers": {
"socialdatax-wechat": {
"type": "streamable_http",
"url": "https://mcp.socialdatax.com/wechat/mcp",
"headers": {
"Authorization": "Bearer "
}
}
}
}A ready-to-copy example is available in `examples/streamable_http_config.json`.
For command/stdio-only MCP clients, use `mcp-remote`:
{
"mcpServers": {
"socialdatax-wechat": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.socialdatax.com/wechat/mcp",
"--header",
"Authorization: Bearer "
]
}
}
}Claude Code can use remote HTTP directly:
claude mcp add --transport http socialdatax-wechat https://mcp.socialdatax.com/wechat/mcp --header 'Authorization: Bearer ${SOCIALDATAX_API_KEY}'Persist `SOCIALDATAX_API_KEY` in the runtime environment or client Secret before restarting Claude Code.
Claude Desktop should use its remote MCP / Connectors UI when available. If a local configuration file in your version only supports command/stdio servers, use the `mcp-remote` fallback.
Client Examples
Configuration examples are available in examples:
- Command/stdio fallback config
- Claude Desktop fallback config
- Cursor remote HTTP config
- Codex remote HTTP config
- Direct streamable HTTP config
API Key
Request or manage API access from the product website:
Use the key as a Bearer token in the `Authorization` request header. Do not commit real API Key values to code, docs, issues, or screenshots.
Directory Metadata
Public metadata files in this repository:
- server-card.json: directory-oriented metadata for the hosted service. Official MCP Registry publishing uses the private source repo's `registry/wechat/server.json` for the current `com.52choujiang/wechat-channels-insights` entry.
- mcp.json: generic command/stdio fallback config using `mcp-remote`.
- glama.json: Glama repository ownership metadata.
- SUBMISSION_CHECKLIST.md: checklist for MCP directory submissions.
License
The files in this public repository are released under the MIT License. The license covers the public documentation and configuration examples in this repository only. It does not cover the managed service implementation, hosted infrastructure, or any private backend code outside this repository.
Frequently asked questions
What is wechat-channels-mcp?
wechat-channels-mcp is 微信视频号 MCP / WeChat Channels MCP by SocialDataX for hot search, video search, details, comments, comment replies, user profiles, user videos, and transcript.
How do I install wechat-channels-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is wechat-channels-mcp open source?
Yes — it is hosted on GitHub at https://github.com/DevinChen2014/wechat-channels-mcp.
Related MCP tools
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP