zai-cli
MCP-native command line interface for Z.AI capabilities: vision analysis, web search, web reader, and GitHub repo exploration.
Links
README
From the repo.
ZAI CLI
MCP-native command line interface for Z.AI capabilities: vision analysis, web search, web reader, and GitHub repo exploration.
Found this useful? Follow @nummanali for more AI tooling!
Features
- Vision - Analyze images, screenshots, diagrams, charts, videos using GLM-4.6V
- Search - Real-time web search with domain and recency filtering
- Reader - Fetch and parse web pages to markdown
- Repo - Search and read GitHub repository code via ZRead
- Tools - MCP tool discovery, schemas, and raw calls
- Code Mode - TypeScript tool chaining for agent automation
Quick Start
export Z_AI_API_KEY="your-api-key"
npx zai-cli --help
npx zai-cli vision analyze ./screenshot.png "What errors do you see?"
npx zai-cli search "React 19 new features" --count 5
Get your API key at: https://z.ai/manage-apikey/apikey-list
Installation
As an Agent Skill
OpenSkills (universal - works with any AI coding agent):
npx openskills install numman-ali/zai-cli
Claude Code (native skill marketplace):
claude skill install numman-ali/zai-cli --skill zai-cli
As a CLI Tool
npm i -g zai-cli
zai-cli --help
Or use directly with npx:
npx zai-cli --help
Usage
The CLI is self-documenting. Use --help at any level:
zai-cli --help # All commands
zai-cli vision --help # Vision commands
zai-cli search --help # Search options
zai-cli repo --help # GitHub repo commands
Examples
# Vision - analyze images
zai-cli vision analyze ./image.png "Describe this"
zai-cli vision ui-to-code ./design.png --output code
zai-cli vision extract-text ./screenshot.png --language python
zai-cli vision diagnose-error ./error.png
# Search - web search
zai-cli search "TypeScript best practices" --count 10
zai-cli search "security news" --recency oneDay
# Reader - fetch web content
zai-cli read https://docs.example.com/api
zai-cli read https://blog.example.com --format text
# Repo - GitHub exploration
zai-cli repo tree facebook/react
zai-cli repo search vercel/next.js "app router"
zai-cli repo read anthropics/anthropic-sdk-python README.md
zai-cli repo search openai/codex "config" --language en
zai-cli repo tree openai/codex --path codex-rs --depth 2
# Doctor - check setup
zai-cli doctor
zai-cli doctor --no-vision
Output Format
Default output is data-only for token efficiency. Use --output-format json for structured responses:
{
"success": true,
"data": "...",
"timestamp": 1234567890
}
Notes
repo searchdefaults to English results. Use--language zhfor Chinese.repo treesupports--path(directory scope) and--depth(expand subtrees).tools,tool,call,doctoraccept--no-visionto speed startup when vision tools are not needed.readsupports--with-images-summary,--no-gfm, and--keep-img-data-urlfor richer parsing control.- Vision tool calls automatically retry transient 5xx/network errors (default: 2 retries). Configure with
ZAI_MCP_VISION_RETRY_COUNT(orZAI_MCP_RETRY_COUNTfor all tools). - Tool discovery can be cached to speed
tools/tool/doctor(default: on, 24h TTL). Configure withZAI_MCP_TOOL_CACHE,ZAI_MCP_TOOL_CACHE_TTL_MS,ZAI_MCP_CACHE_DIR.
Repository Layout
├── packages/zai-cli/ # npm package source
├── skills/zai-cli/ # Agent skill (SKILL.md)
└── .claude-plugin/ # Claude Code marketplace config
Development
cd packages/zai-cli
npm install
npm run build
npm test
node scripts/bench-tools.mjs
Contributing
See CONTRIBUTING.md for development setup and guidelines.
License
MIT - see LICENSE.
Links
Collected info
- ★ 110 stars
- ⎇ 13 forks
- Language: TypeScript
- Source updated: 9/21/2026
Config for your environment
Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.
Tool
OS
Config file: ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"url": "{MCP_ENDPOINT_URL}"
}
}
}Paste into mcpServers in the config file. Restart Cursor after saving.
If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.