AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified Apache-2.0 Self-run

Modus

mcp-brandlll-lee-modus · by brandlll-lee

Open source coding agent workspace, an agent-first desktop app that runs locally. alternative to Cursor and Codex.

↗ Repository
— No reviews yet
0 installs
25 views
0.0% view→install

Install

$ agentstack add mcp-brandlll-lee-modus

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-brandlll-lee-modus)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Modus? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

English | 简体中文

Modus

Local-first desktop workspace for AI coding agents.

Getting started · Features · Security

About

Modus is an open-source desktop app for running AI coding agents inside real local projects.

Open a workspace, connect your own model provider, plan or build, inspect changes, approve risky actions, and keep the full workflow in one window.

Modus is early and currently runs best from source.

Features

  • Workspaces and sessions - Open local projects, switch recent workspaces, pin projects, and keep separate agent sessions per repo.
  • Bring your own models - Configure built-in or custom PI-compatible providers, defaults, reasoning effort, thinking variants, and model limits.
  • Git workflow - Review working tree changes, file diffs, branches, commit history, commits, pushes, and session change stats.
  • Terminal, browser, and files - Use a real PTY terminal, an in-app browser with tabs and DevTools, and a workspace file explorer.
  • Fast Codebase - Let the agent build a compact local code map before reading files, reducing broad grep/read exploration.
  • Subagents - Create specialized subagents, track their activity, and apply or clean up their worktrees.
  • Plan and build modes - Start with a reviewable plan, answer structured questions, then move into implementation.
  • Context and images - Attach files, folders, docs, Git diffs, terminal output, browser state, selected page elements, rules, and images.
  • MCP, skills, and rules - Load Modus MCP servers, invoke local skills with /, and apply project rules from AGENTS/Claude/Cursor-style files.
  • Permissioned execution - Route shell, Git, browser, MCP, file, and external actions through one approval flow.
  • Checkpoints and rollback - Snapshot the workspace before agent runs and restore from the timeline when needed.

Getting Started

Requirements for Windows and macOS:

  • Node.js >= 22.19.0
  • npm
  • Rust + Cargo
  • Git
git clone https://github.com/brandlll-lee/modus.git
cd modus
npm install
npm run dev

Then open a workspace folder and configure a model provider in Settings.

Development

npm run dev
npm run check
npm run test
npm --workspace @modus/desktop run typecheck
npm --workspace @modus/desktop run build

Package locally:

npm --workspace @modus/desktop run package:win -- --publish never
npm --workspace @modus/desktop run package:mac -- --publish never

Run the Windows command on Windows and the macOS command on macOS.

MCP Config

Modus only auto-loads its own MCP config files:

~/.modus/mcp.json
/.modus/mcp.json

It does not silently import Cursor, Claude, Warp, or other agent configs.

Tech Stack

Electron, React, TypeScript, Tailwind CSS, Base UI, Motion, Monaco, xterm.js, Streamdown, Node SQLite, Rust portable-pty, @earendil-works/pi-coding-agent, and the MCP SDK.

Contributing

Contributions are welcome. Keep PRs small, use Conventional Commits, and run npm run check plus npm run test before opening a PR.

License

Apache-2.0. See [LICENSE](./LICENSE).

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML