SkillsMay 13, 2026·2 min read

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.

Agent ready

Safe staging for this asset

This asset is staged first. The copied prompt tells the agent to inspect the staged files and ask before activating scripts, MCP config, or global config.

Stage only · 29/100Policy: stage
Agent surface
Any MCP/CLI agent
Kind
Skill
Install
Stage only
Trust
Trust: Established
Entrypoint
Asset
Safe staging command
npx -y tokrepo@latest install 29ad7b32-0d55-50f7-a4ea-73b742b4fa66 --target codex

Stages files first; activation requires review of the staged README and plan.

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

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets