communication MCP Server
WeChat/微信 local chat history MCP server for macOS agents. Read messages, contacts, media, favorites, transfers, red packets, Moments and full-text search from local WeChat 4.x data.
Discovered via github-seeds:mcp-hot and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
说明
朋友圈正文搜索, keyword 必填, 字段同 sns
WCDB 数据库结构. 不传参列所有 db 子目录 + 表名; 传 subdir+file 返回每张表 DDL
最近会话、未读数、最后消息摘要
把昵称/备注/alias/群名解析成 username/talker. 返回 candidates, 供 agent 从自然语言目标进入精确工具调用
联系人/群搜索. 字段: username / display_name / nick_name / remark (omitempty) / alias (omitempty) / description (omitempty) / type / chat_type / is_verified
消息附件/媒体资源定位. 从 `message_resource.db` 返回 `server_id_str`、图片/视频/文件/封面资源的 raw type、variant_code、size、status、packed_strings(文件名/md5) 和已存在的本地 `local_paths`. 支持 chat/talker/local_id/server_id/server_id_str/type/resource_family 过滤
朋友圈时间线, 语义化 alias, 字段同 sns
朋友圈点赞/评论通知. 默认未读; include_read=true 返回全部
走微信本地 FTS 的跨会话全文搜索
只读 SQL. `SELECT/WITH` 默认外层限流, `limit` 最大 1000; `PRAGMA/EXPLAIN` 可直接跑. OS 级 readonly (SQLITE_OPEN_READONLY) — DDL/DML 直接报错
红包. 字段: send_id / sender_wxid / session_username / native_url / message_server_id / **wishing** ("恭喜发财大吉大利") / scene_text. 支持 chat/talker/sender/after/before; 时间/sender 过滤使用 cache join messages.create_time
**最近转发目标列表** (用于快捷转发, 非"被转发的消息历史"). 字段: username / display_name / forward_time
查看明文 snapshot cache 与统一 index.sqlite 状态. 不触发 wxkey setup
刷新 snapshot cache 并重建 index.sqlite. 默认按 DB/WAL mtime 复用未变化 snapshot; force=true 强制重解; background=true 立即返回并在后台刷新
删除当前 cache 后完整重建
增量拉新消息. 支持 chat/talker/after/cursor, 返回 messages + next_cursor. cursor 是 `v2:create_time:base64url_talker:local_id`, 不依赖 cache rebuild 后会漂移的 SQLite rowid
消息. talker 可传 wxid; chat 可传昵称/备注/群名自动解析. fields=lite (默认) 返回核心字段; fields=full 加 subtype + raw message_content + message_content_parsed (XML 结构化, 引用递归 depth=3). content_summary 已剥群聊 sender prefix
群成员. chatroom_id 可传群 ID; chat 可传群名自动解析. is_owner / is_friend 是 bool. stats=true 附 msg_count
朋友圈 + 点赞/评论. 字段: tid / username / nickname / avatar_url / create_time / content / type / private / liked_by_me / media (含 raw_type/sub_type/url_key/thumb_key/md5/width/height/total_size/video_md5/video_duration) / location / likes / comments
转账. 字段: transfer_id / transcation_id / payer_wxid / receiver_wxid / session_username / pay_sub_type / begin_transfer_time / **amount** ("￥5.00") / **description** ("收到转账5.00元") / memo (omitempty). amount/description/memo 是 batch join messages.server_id 解 XML 提取
微信收藏
群公告. 字段: chatroom_id / chatroom_display_name / announcement / editor_wxid / editor_display_name / publish_time
未读会话列表, 字段同 sessions. 支持 filter/type_filter=private,group 等
metadata cache 计数，不是消息趋势统计
从 cache index 导出消息到 jsonl / markdown / html 文件. 支持 chat/talker/after/before/keyword
WeChat Read OS 总入口：覆盖率矩阵、工作流、质量验收、本机状态
更新到 GitHub latest release
把昵称、备注、群名解析成稳定 talker
以 `local_id` / `server_id` 为锚点展开前后消息
blocked`；如果 metadata cache 可用但已滞后，会返回 `warnings=["metadata_cache_degraded"]` 和具体 stale reason。 `agent` 是 agent 进入微信读取环境的总入口。它返回当前能力矩阵、推荐工作流、质量验收命令和本机 readiness，不会读取大量聊天正文，也不会修改微信数据；`read-os` 仍是兼容别名： ```bash wechat-cli agent --pretty wechat-cli status --pretty wechat-cli coverage --pretty wechat-cli workflows --pretty ``` 搜索或 timeline 拿到某条消息后，用 `context` 自然展开上下文： ```bash wechat-cli search "$KEYWORD" --in "$CHAT" --limit 5 --pretty wechat-cli context "$CHAT" --local-id 123 --before-count 20 --after-count 20 --pretty wechat-cli search-context "$KEYWORD" --in "$CHAT" --context-limit 3 --pretty wechat-cli timeline "$CHAT" --before-message 123 --limit 20 --pretty ``` `context` 返回的 `messages[]` 与 `timeline` 同形，额外带 `context_role=before/anchor/after`，用于让 agent 从一句话继续向前向后读。`search-context` 是 `search -> context` 的组合入口；`timeline --before-message/--after-message` 则把 `local_id` 当游标翻更旧或更新的消息。 小助手增量观察用 `tail` / `watch`。它仍然是 read-only：不发消息、不控制 UI。传 chat 时返回 message events，`event.message` 与 timeline message 行同形；不传 chat 时返回 session/unread events。普通模式返回标准 envelope；`--jsonl`/`--follow` 输出一行一个 event，不包 envelope。`cursor` 可原样传回下一次调用： ```bash wechat-cli tail "$CHAT" --since-local-id 123 wechat-cli tail "$CHAT" --since-local-id 123 --jsonl wechat-cli watch --mode sessions --cursor session:1780560000 --jsonl wechat-cli watch "$CHAT" --cursor local_id:123 --jsonl --follow ``` ## 常用命令
默认列 assistant 高信噪比工具；`--profile all` 列全部兼容/维护工具
普通读聊天的首选入口，返回 `query` / `freshness` / `messages`
更底层的消息读取，支持时间、类型、sender、分页等过滤
搜索并自动展开每个命中附近上下文
按消息定位图片、视频、文件等本机可读资源
群成员、群名片、好友关系
显式本地文件写入：单个会话导出到 jsonl / markdown / html
Send messages and upload files to Slack channels using the `slack` CLI. Supports direct messages, channel posts, file uploads, and thread replies.
Bidirectional Telegram bridge — talk to Claude from your phone. Built into OpenPaw.
Discover agents across local node and mesh peers at runtime — their roles, handles, and how to communicate with or delegate to them.
Apply data visualization and storytelling principles from Storytelling with Data by Cole Nussbaumer Knaflic. Covers choosing effective visuals (line, bar, table, scatterplot), eliminating clutter (Gestalt principles, data-ink ratio), focusing attention (preattentive attributes, strategic color), thinking like a designer (affordances, alignment, white space), and narrative structure (three-act story, horizontal/vertical logic, Big Idea). Trigger on "data visualization", "chart design", "dashboard design", "data storytelling", "presentation chart", "declutter chart", "bar chart", "line chart", "data narrative", "slide deck data", "chart review", "viz critique", "storytelling with data".
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
AgentNetworkProtocol(ANP) is an open source protocol for agent communication. Our vision is to define how agents connect with each other, building an open, secure, and efficient collaboration network for billions of intelligent agents.
Learn how to use the c-slack Claude skill. Complete guide with installation instructions and examples.
Learn how to use the c-telegram Claude skill. Complete guide with installation instructions and examples.
Learn how to use the Letter Writer Claude skill. Complete guide with installation instructions and examples.