Omnisockit Mcp

io.github.OmniSocKitPublished by GitHub account OmniSocKitv0.1.5Updated Oct 24, 2026

Turn your AI into a WeCom development expert. 41 SKILLs, 550+ APIs.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Serves WeCom (Enterprise WeChat) development knowledge as MCP resources so an assistant can write accurate integration code instead of guessing API details.

What you can do
  • Read WeCom development skill documents on demand, covering 41 skills and 550+ APIs
  • Look up guidance on access tokens, OAuth login, messaging, error codes and customer tags
  • Get code templates in Python, Node.js, Java, Go and PHP
  • Cover in-enterprise development, ISV service-provider and third-party app modes
  • Expose each skill as a separate MCP resource that the assistant loads only when needed
When to use it
Useful when you are building a WeCom integration and want the assistant to produce code that respects real token caching, rate limits, error codes and parameter constraints rather than hallucinated API details.
Requirements
Runs locally over stdio via npx from the npm package; Node.js and network access for the package download are needed. No API key, server or Docker required according to the README.
Before you install
The server only supplies documentation and does not call WeCom APIs itself; you run any generated code yourself. Review generated code before use, since it handles credentials such as access tokens and OAuth flows.

Installation

In SourceWeft

  1. Open Omnisockit Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

OmniSocKit MCP Server

让你的 AI 大模型成为社交营销平台开发专家。

[License] [Node.js] [Skills]

中文 | English

什么是 OmniSocKit？

OmniSocKit 是一个 MCP (Model Context Protocol) Server，将社交营销平台的开发知识注入到你的 AI 工具中。

安装后，当你对 AI 说「帮我实现企微 OAuth 登录」，AI 能给出包含正确 Token 缓存、错误重试、频率限制处理的精确代码——而不是幻觉。

核心价值

  • 🎯 精准编码 — AI 不再猜测 API 参数，因为它读过完整的 SKILL 文档
  • 🛡️ 避免踩坑 — 每个 SKILL 包含真实的约束、限制、错误码处理
  • ⚡ 零配置 — 不需要 API Key、不需要服务器、不需要 Docker
  • 🔒 零风险 — 不调用任何 API，只提供知识

快速开始

在你的 AI 工具中添加以下配置：

json
{  "mcpServers": {    "omnisockit": {      "command": "npx",      "args": ["@omnisockit/mcp-server"]    }  }}

安装完成。现在对 AI 说：

"帮我实现企微 OAuth 扫码登录"

AI 会自动读取相关 SKILL，给出包含所有约束的精确代码。

支持的 AI 工具

OmniSocKit 兼容所有支持 MCP 协议的 AI 工具：

工具类型配置示例
Claude Desktop桌面应用查看
Claude CodeCLI查看
CursorAI IDE查看
Antigravity桌面应用查看
WindsurfAI IDE查看
VS Code + CopilotIDE查看
TraeAI IDE查看
ClineVS Code 插件查看
Roo CodeVS Code 插件查看
Kilo CodeVS Code 插件查看
ContinueVS Code / JetBrains查看
Cherry Studio桌面应用查看
Zed编辑器查看
OpenAI Codex CLICLI查看

💡 只要支持 MCP 协议的工具都可以使用，以上仅列出主流工具。

覆盖的平台

✅ 企业微信（免费）

维度数据
SKILL 数量41 个
覆盖模式企业内部开发 · 服务商代开发（ISV）· 第三方应用
API 覆盖550+ 接口
代码模板五语言（Python / Node.js / Java / Go / PHP）

🔜 更多平台（即将推出）

  • 小红书
  • 抖音 / TikTok
  • 微信公众平台
  • 飞书

常见场景

你对 AI 说AI 读取的 SKILLAI 回答包含
"帮我获取企微 access_token"wecom-coreToken 缓存规则、7200s 有效期、多实例互踢
"帮我实现企微扫码登录"wecom-authOAuth URL 格式、code 有效期 5 分钟、redirect_uri 编码
"企微发消息怎么做"wecom-messagemsgtype 类型、agentid 必填、频率限制
"企微 errcode 42001"wecom-coreToken 过期原因、多实例部署 Token 互踢
"企微客户标签怎么管理"wecom-crm-tag标签上限、企业标签 vs 个人标签

工作原理

┌──────────────────────────────────────────┐│           你的 AI 工具                     ││  (Claude / Cursor / VS Code / ...)       ││                                          ││  用户: "帮我实现企微 OAuth 登录"            ││                                          ││  AI 判断需要 wecom-auth 的知识             ││  ↓ 通过 MCP 协议读取                      │└──────────────┬───────────────────────────┘               │ stdio (JSON-RPC)┌──────────────▼───────────────────────────┐│        OmniSocKit MCP Server             ││                                          ││  41 个 SKILL → 41 个 MCP Resource         ││  AI 按需读取，不是全量加载                   ││                                          ││  返回 wecom-auth SKILL 的完整内容           │└──────────────────────────────────────────┘               ↓  AI 基于 SKILL 知识生成精确代码  用户拿代码自己执行（我们不碰 API）

项目结构

omnisockit-mcp/├── packages/│   ├── core/                 ← 核心类型定义│   ├── platform-wecom/       ← 企微 41 个 SKILL│   ├── server/               ← MCP Server 引擎│   ├── cli/                  ← npx 入口│   └── execution/            ← 🔜 API 执行层（预留）├── examples/                 ← 14 个 AI 工具配置示例└── tests/                    ← 单元测试

许可证

Apache License 2.0

链接

Source: README.md at commit eb662d4

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.5LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts