Ohos Unofficial
FreeNot checkedBrings HarmonyOS and OpenHarmony English documentation to AI assistants for instant retrieval and multimodal analysis.
About
Brings HarmonyOS and OpenHarmony English documentation to AI assistants for instant retrieval and multimodal analysis.
README
Project Status: Active License: MIT
This is an unofficial Model Context Protocol (MCP) server that brings the power of HarmonyOS & OpenHarmony English Documentation directly to your AI assistants. It indexes over 5,000 official documentation files for instant, high-context retrieval.
🚀 Quick Start: Zero-Install Method (Recommended)
The easiest way to use this is via npx. No cloning required!
1. Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"ohos-docs": {
"command": "npx",
"args": ["-y", "github:megaacheyounes/ohos-mcp-unofficial"]
}
}
}
2. ChatGPT Codex CLI
Add the server using the following command:
codex mcp add ohos -- npx -y github:megaacheyounes/ohos-mcp-unofficial
3. OpenCode AI
In the OpenCode settings or config:
- Command:
npx - Arguments:
-y github:megaacheyounes/ohos-mcp-unofficial
4. Cursor / Windsurf / IDEs
Add a new MCP server in the settings:
- Type:
command - Command:
npx -y github:megaacheyounes/ohos-mcp-unofficial
5. Gemini CLI
In your .geminirc:
{
"mcpServers": {
"ohos": {
"command": "npx",
"args": ["-y", "github:megaacheyounes/ohos-mcp-unofficial"]
}
}
}
🖼️ Multimodal Support
The documentation has been optimized for AI agents with "vision" capabilities.
- Remote Images: All diagrams and screenshots are linked directly to the official Gitee repository.
- Agent Action: Multimodal agents can follow these links to download and analyze visual architecture diagrams, UI mockups, and flowcharts to provide more accurate explanations.
🌐 Understanding the Two Modes
1. Stdio Mode (Default)
Used by local assistants (Claude Desktop, Cursor, etc.). The assistant starts the server as a background process.
2. HTTP Mode
Use this for remote access or web integrations.
# Start server
npx -y github:megaacheyounes/ohos-mcp-unofficial --http --port 3456
- Health Check:
http://localhost:3456/health - Tool Calls: POST to
http://localhost:3456/call
🧰 Available Tools
find_docs: Search documentation by keywords (e.g., "Navigation", "Canvas").read_doc: Retrieve the full Markdown content of a specific document.list_doc_topics: Browse the documentation hierarchy.
🌟 Credits
Inspired by arkts-helper. This version is specifically optimized for the English-speaking community using OpenHarmony 6.1 (API 23) open-source documentation.
⚖️ Disclaimer
This is an unofficial community project and is not affiliated with, maintained by, or endorsed by Huawei Technologies Co., Ltd. or the OpenHarmony project.
Parts of this project were generated or assisted by AI.
Use of this tool and the documentation it retrieves is at your own risk. Always verify critical information against the official documentation.
📄 License
MIT © megaacheyounes
Installing Ohos Unofficial
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/megaacheyounes/ohos-mcp-unofficialFAQ
Is Ohos Unofficial MCP free?
Yes, Ohos Unofficial MCP is free — one-click install via Unyly at no cost.
Does Ohos Unofficial need an API key?
No, Ohos Unofficial runs without API keys or environment variables.
Is Ohos Unofficial hosted or self-hosted?
A hosted option is available: Unyly runs the server in the cloud, no local setup required.
How do I install Ohos Unofficial in Claude Desktop, Claude Code or Cursor?
Open Ohos Unofficial on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare Ohos Unofficial with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
