# Zread > AI-powered CLI and MCP server for browsing GitHub project documentation (unofficial tool) - **Type:** MCP server - **Install:** `agentstack add mcp-ejfkdev-zread` - **Verified:** Yes β€” security-reviewed for prompt injection and unsafe behavior - **Seller:** [ejfkdev](https://agentstack.voostack.com/s/ejfkdev) - **Installs:** 0 - **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [ejfkdev](https://github.com/ejfkdev) - **Source:** https://github.com/ejfkdev/zread - **Website:** https://zread.ai ## Install ```sh agentstack add mcp-ejfkdev-zread ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Zread - AI Repository Reading Assistant [δΈ­ζ–‡](README.zh.md) | English [](https://www.python.org/) [](https://zread.ai/ejfkdev/zread) [](https://modelcontextprotocol.io/) [](https://pypi.org/project/zread/) [](https://github.com/ejfkdev/zread) [](https://github.com/ejfkdev/zread) [](https://pypi.org/project/zread/) [](https://pypi.org/project/zread/) [](LICENSE) Zread helps you and your AI understand codebases faster. Skip the manual source dive and ask directly. It connects to [Zread.ai](https://zread.ai), an AI-powered GitHub project documentation service. **Two roles**: - πŸ–₯️ **CLI tool** - run directly in your terminal with minimal setup - πŸ”Œ **MCP server** - integrate with AI assistants such as Claude and Cline **Highlights**: - πŸ” Browse docs, search code, and discover repositories without a token - πŸ€– AI Q&A powered by repository documentation - 🌐 Multiple transports: stdio, HTTP, and SSE - ⚑ One command to run, zero-friction startup ## Features - πŸ“– **Read docs** - browse GitHub repository docs directly in the terminal - πŸ” **Search docs** - search keywords across repository documentation - 🌟 **Discover repos** - browse trending rankings and recommended projects - πŸ“₯ **Export docs** - export repository docs locally and generate `llms.txt` and `llms-full.txt` (CLI only) - πŸ€– **AI Q&A** - ask the repository AI assistant questions (requires a free account token) - πŸ“„ **Read source files** - inspect source file contents directly - πŸ”Œ **MCP integration** - connect seamlessly with AI assistants ## Screenshots Help zread -h Documentation Outline zread ls openclaw/openclaw Read a Doc Page zread cat openclaw/openclaw Read a GitHub File zread cat facebook/react README.md Search Repositories zread find ai sandbox Search Documentation zread find openclaw/openclaw gateway Trending Repos zread top Random Recommendation zread rand agent-skills Single-turn AI Q&A zread ai openclaw/openclaw "introduce this project briefly" Interactive AI Chat zread ai openclaw/openclaw Export Repository Docs zread cp openclaw/openclaw MCP HTTP Service zread mcp http :8080 ## Quick Start ### CLI Tool ```bash # Run with uvx uvx zread # Or with pipx pipx run zread ``` ### MCP Server ```bash # stdio mode uvx zread mcp # HTTP mode uvx zread mcp http ``` ### AI Q&A AI Q&A requires a free token from your [Zread.ai](https://zread.ai) account. **Set your token:** ```bash export ZREAD_TOKEN=your-token ``` **Usage:** ```bash # Interactive multi-turn chat zread ai openclaw/openclaw # Single question zread ai facebook/react "How is this project structured?" ``` ## CLI Commands ```bash # Start the MCP server zread mcp [stdio|http|sse] [address] [options] # Show the documentation outline zread ls [-l zh|en] [-j] [-p] # Read a documentation page or a source file zread cat [slug_or_path] [-l zh|en] [-j] [-p] # # Automatic argument detection: # - If the first argument is only repo and the second is a slug/index (for example 1-overview, 1), it reads a zread doc page # - Other forms (for example README.md, owner/repo/README.md#L1-10, github.com/owner/repo/README.md#L1-10) read a GitHub file # Search zread find # Search GitHub repositories zread find # Search within a repository's docs # Discover recommended repositories zread rand [topic] [-l zh|en] [-j] [-p] # Show trending repositories zread top [weeks] [-l zh|en] [-j] [-p] # Show repository status and metadata (silently submits unindexed repos and refreshes stale docs) zread stat [-l zh|en] [-j] [-p] # Ask the repository AI (requires a free account token) zread ai [question] [-l zh|en] [-t token] [-p] [-j] [-m model] # Export repository docs locally and generate llms.txt / llms-full.txt zread cp [output_dir] [-l zh|en] [-c concurrency] ``` ### Global Options The CLI supports plain text and JSON output and works well in pipelines: | Option | Description | | -------------------- | ---------------------------------------------------------------------- | | `-l, --lang {zh,en}` | Language priority: `--lang` > `ZREAD_LANG` > system locale, default `en`. | | `-j, --json` | Output as JSON | | `-p, --plain` | Output plain text | | `-t, --token` | ZREAD_TOKEN | | `-h, --help` | Show help | | `-v, --version` | Show version | ### Examples ```bash # MCP server uvx zread mcp # stdio mode (default) uvx zread mcp http # HTTP mode uvx zread mcp http :8080 # Custom port uvx zread mcp http 0.0.0.0:3000/custom # Custom address and path # Docs uvx zread ls golang/go uvx zread cat vuejs/vue uvx zread cat vuejs/vue 1 uvx zread cat vuejs/vue 1-overview uvx zread cat golang/go README.md uvx zread cat python/cpython Lib/http/client.py uvx zread cat github.com/facebook/react/README.md#L1-10 uvx zread cat facebook/react/README.md#L1-10 uvx zread cat facebook/react README.md 5 10 uvx zread cat facebook/react README.md 5-10 uvx zread cat facebook/react README.md 5~ uvx zread cat facebook/react/README.md 5: uvx zread find facebook/react hooks # Discovery uvx zread top uvx zread top 4 uvx zread rand python uvx zread rand awesome-list # Repository info uvx zread stat torvalds/linux # AI Q&A uvx zread ai golang/go "How do I choose between channels and mutexes?" -t your-token uvx zread ai python/cpython --model claude-sonnet-4.6 -t your-token uvx zread ai rust-lang/rust # Export docs uvx zread cp golang/go uvx zread cp python/cpython -l zh uvx zread cp vuejs/vue -c 20 ``` ## MCP Client Configuration Add the following configuration to any MCP-compatible client: ```json { "mcpServers": { "zread": { "command": "uvx", "args": ["--env", "ZREAD_TOKEN=your-token", "zread", "mcp"] } } } ``` ## MCP Tools | Tool | Description | | ----------------- | --------------------------------------------------------------------------- | | `read_doc` | Get the content of a specific documentation page | | `search_wiki` | Search keywords in repository documentation | | `get_doc_outline` | Get the repository documentation outline | | `discover_repo` | Discover a recommended repository at random | | `get_trending` | Get trending repository rankings | | `get_repo_info` | Get repository information and indexing status | | `read_source_file`| Read source code file contents | | `ask_ai` | Ask the repository AI a question (token required), supports `glm-5.1` and `claude-sonnet-4.6` | ## Get a Token AI Q&A requires a free JWT token from your Zread.ai account: 1. Visit https://zread.ai and sign in 2. Press F12 to open the browser console 3. Run: ```javascript prompt( "copy token", JSON.parse(localStorage.getItem("CGX_AUTH_STORAGE")).state.token, ); ``` 4. Copy the token from the popup dialog ## Environment Variables | Variable | Description | | -------------- | ------------------------------------------------------------------ | | `ZREAD_TOKEN` | Free JWT token from your zread.ai account, only required for AI Q&A | | `ZREAD_LANG` | Default language (`zh` / `en`), lower priority than `--lang` and higher than system locale | | `ZREAD_MODEL` | Default AI model (`glm-5.1` / `claude-sonnet-4.6`), lower priority than `--model` | ## Configuration File You can also configure zread using a config file. The priority is: **CLI arguments > Environment variables > Config file**. **Config file locations:** - macOS: `~/.config/zread/zread.toml` - Linux: `$XDG_CONFIG_HOME/zread/zread.toml` (if set) or `~/.config/zread/zread.toml` - Windows: `%APPDATA%\zread\zread.toml` **Config file format (TOML):** ```toml [zread] token = "your-token-here" lang = "zh" # optional, defaults to "zh" model = "glm-5.1" # optional, defaults to "glm-5.1", also supports "claude-sonnet-4.6" ``` ## Contributing Contributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for details. ## License MIT License. See [LICENSE](LICENSE) for details. ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source β€” we do not rehost the code. - **Author:** [ejfkdev](https://github.com/ejfkdev) - **Source:** [ejfkdev/zread](https://github.com/ejfkdev/zread) - **License:** MIT - **Homepage:** https://zread.ai Install and usage instructions live in the source repository linked above. ## Pricing - **Free** β€” Free ## Security capabilities Automated source analysis of v0.1.0 β€” what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source β€” more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** β€” security scan: passed β€” Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-ejfkdev-zread - Seller: https://agentstack.voostack.com/s/ejfkdev - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack β€” the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.