# VT Code — Multi-Provider Coding Agent with MCP

> VT Code is an open-source coding agent with multi-provider support, shell safety, and docs for Skills, ACP, and MCP integration.

## Install

Copy the content below into your project:

## Quick Use

```bash
curl -fsSL https://raw.githubusercontent.com/vinhnx/vtcode/main/scripts/install.sh | bash
export OPENAI_API_KEY="sk-..."
vtcode
# optional: vtcode dependencies install search-tools
```

## Intro

VT Code is an open-source coding agent with multi-provider support, shell safety, and docs for Skills, ACP, and MCP integration.

**Best for:** developers who want a CLI coding agent with extensible skills and protocol integrations

**Works with:** macOS/Linux/Windows, multiple LLM providers, MCP-capable clients, Zed via ACP

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub: 588 stars · 49 forks · pushed 2026-05-13.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-verified entrypoint: `cargo install vtcode`.

## Main

- Use the native installer for a fast start, then run `vtcode` with the provider env var you already use (README shows OpenAI as an example).

- If you rely on semantic search, install the optional bundle and keep `ripgrep` + `ast-grep` available as recommended by the README.

- When integrating with editors or other agents, follow the README guides for MCP and ACP so your agent runs are reproducible across machines.

### Source-backed notes

- README documents install options: native installer script, `cargo install vtcode`, and `brew install vtcode`.
- README shows a minimal run: set `OPENAI_API_KEY` then `vtcode`.
- README includes guides/badges for MCP integration and Agent Skills support.

### FAQ

- **Do I have to use OpenAI?**: No — README lists multiple providers and shows OpenAI only as an example.
- **Can I install via Homebrew?**: Yes — README includes `brew install vtcode` (and an optional tap path).
- **Does it support MCP?**: Yes — README links to an MCP integration guide.

## Source & Thanks

> Source: https://github.com/vinhnx/VTCode
> License: MIT
> GitHub stars: 588 · forks: 49

---

<!-- ZH -->

## Quick Use

```bash
curl -fsSL https://raw.githubusercontent.com/vinhnx/vtcode/main/scripts/install.sh | bash
export OPENAI_API_KEY="sk-..."
vtcode
# optional: vtcode dependencies install search-tools
```

## Intro

VT Code 是开源编程 agent，强调多模型提供方、Shell 安全与上下文管理，并提供 Skills、编辑器协议（ACP）与 MCP 集成文档；README 展示安装脚本与最小示例（设置 API key 后直接运行 `vtcode`）。

**Best for:** 想要可扩展技能、并能接入协议生态的 CLI 编程 agent 用户

**Works with:** macOS/Linux/Windows；多模型提供方；MCP 客户端；Zed（ACP）

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub：588 stars · 49 forks；最近更新 2026-05-13。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中核对过的入口命令：`cargo install vtcode`。

## Main

- 按 README 用官方安装脚本快速装好，再用你已有的提供方环境变量启动（README 以 OpenAI 为例）。

- 需要语义搜索时按 README 建议补齐 `ripgrep` + `ast-grep`，再装 search-tools bundle。

- 要接入编辑器或其他 agent 时，优先按 README 的 MCP/ACP 指南配置，保证跨机器可复现。

### Source-backed notes

- README 提供安装方式：官方安装脚本、`cargo install vtcode`、以及 `brew install vtcode`。
- README 给出最小运行示例：设置 `OPENAI_API_KEY` 后执行 `vtcode`。
- README 包含 MCP 集成与 Agent Skills 支持的指南入口。

### FAQ

- **必须用 OpenAI 吗？**：不必须。README 列出多种提供方；OpenAI 只是示例。
- **能用 Homebrew 装吗？**：能。README 提供 `brew install vtcode`（也给出可选 tap 方式）。
- **支持 MCP 吗？**：支持。README 提供 MCP 集成指南链接。

## Source & Thanks

> Source: https://github.com/vinhnx/VTCode
> License: MIT
> GitHub stars: 588 · forks: 49


---
Source: https://tokrepo.com/en/workflows/vt-code-multi-provider-coding-agent-with-mcp
Author: Agent Toolkit