Code Assistant MCP server
Commit 13 Nov 2026Memungkinkan AI client menjalankan autonomous coding agent yang dapat membaca, mencari, mengedit file, dan menjalankan command di dalam project Anda.
Juga dikenal sebagai stippi/code-assistant
- Stars
- 190
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 13 Nov 2026
- Lisensi
- MIT
Apa itu Code Assistant MCP?
Code Assistant adalah MCP server. Memungkinkan AI client menjalankan autonomous coding agent yang dapat membaca, mencari, mengedit file, dan menjalankan command di dalam project Anda.
Ringkasan dibuat dari README proyek
Tentang Code Assistant MCP server
Tool ini memungkinkan Anda menjalankan autonomous coding agent yang mengelola codebase secara langsung dari AI client. Ia berfungsi sebagai jembatan yang memungkinkan model untuk membaca, mencari, mengedit file, dan mengeksekusi command di dalam project lokal Anda. Developer dapat menggunakannya melalui GUI native, interface terminal, atau sebagai headless MCP server untuk client seperti Claude Desktop. Tool ini juga mendukung mode ACP agent untuk editor seperti Zed.
Untuk memulai, Anda cukup memilih provider LLM seperti Anthropic, OpenAI, atau Google Vertex AI dan memasukkan API key Anda melalui layar settings. Sistem ini dirancang agar transparan, dengan menampilkan secara jelas tool mana yang sedang berjalan dan context apa yang dikembalikan. Tool ini mampu menangani tugas kompleks seperti menyelaraskan edit file dengan auto-formatter serta membaca dokumen non-code seperti PDF atau Excel dengan mengonversinya ke Markdown. Hal ini memastikan agent tetap memiliki gambaran mental yang akurat tentang project Anda tanpa membuang-buang token untuk pembacaan ulang yang tidak perlu.
Apa yang bisa Anda lakukan dengannya
- 1Eksplorasi codebase otomatisMinta agent untuk menjelaskan struktur dan logika dari sebuah repository yang kompleks.
- 2Pengembangan terintegrasi dokumenInstruksikan agent untuk menggunakan dokumentasi project seperti file PDF atau Word sebagai acuan dalam pengambilan keputusan coding.
- 3Testing aplikasi webBiarkan agent mengendalikan browser asli untuk menavigasi dan berinteraksi dengan aplikasi web Anda.
- 4Editing code berbasis contextMelakukan edit file yang tetap konsisten meskipun project Anda menggunakan automatic code formatting.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Konfigurasi
ANTHROPIC_API_KEY
| Nama | Deskripsi | Tipe |
|---|---|---|
| ANTHROPIC_API_KEY | — |
Pengecekan otomatis
Berjalan 12 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkauLolos
- Lisensi open source (OSI)Lolos
- Ada commit atau release dalam satu tahun terakhirLolos
- Nama package tidak mirip dengan package populerTidak diperiksa
- Remote endpoint menggunakan HTTPSTidak diperiksa
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Tidak ada instruksi tersembunyi untuk modelLolos
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
README
Lihat di GitHubCode Assistant
An open-source AI coding agent, written in Rust, with a native GUI, a terminal mode, and integrations for editors and MCP clients. It runs an autonomous agent loop over your codebase — reading, searching, editing files, and running commands — while keeping you in the loop about what it is actually doing.
Getting started
The quickest way to try it is a prebuilt download — no toolchain required:
- Grab the latest build from the Releases page:
- macOS:
Code-Assistant-macos-aarch64.app.zip(Apple Silicon) orCode-Assistant-macos-x86_64.app.zip(Intel) - Linux:
code-assistant-linux-x86_64.zip - Windows:
code-assistant-windows-x86_64.zip
- macOS:
- Launch it. On first start, code-assistant opens its Settings screen. Pick a provider (there are one-click suggestions for the common ones), paste an API key, and choose a model — that's it.
- Add your project folder from within the app and start a chat.
No hand-editing of JSON files required to get going. (You still can, if you prefer — see the Configuration guide.)
# Install the Rust toolchain (macOS/Linux)
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
# On Linux (Debian/Ubuntu), install the system libraries gpui needs:
sudo apt-get install -y --no-install-recommends \
pkg-config build-essential libssl-dev libzstd-dev \
libfontconfig-dev libwayland-dev libx11-xcb-dev \
libxkbcommon-x11-dev libasound2-dev libvulkan1
# On macOS, install the metal toolchain:
xcodebuild -downloadComponent MetalToolchain
# Clone and build
git clone https://github.com/stippi/code-assistant
cd code-assistant
cargo build --release
The binary lands at target/release/code-assistant. See the
Configuration guide for building a self-contained
macOS .app bundle.
What makes it different
A handful of things we care about:
- A UI you can actually follow. Instead of a terse "Called 5 tools", code-assistant shows which tools ran and what each of them handed back to the model as context. When it goes off the rails, you can see why.
- Format-on-save that stays token-efficient. When your project auto-formats code, an agent's mental picture of a file goes stale and its follow-up edits start failing for non-obvious reasons. code-assistant runs your formatter and then reconciles the model's own edits with the formatted result — without wasting tokens on re-reading files. See docs/format-on-save-feature.md.
- Transparent file encoding & line endings. It reads a file however it is stored (encoding, BOM, CRLF/LF), gives the model clean text, and writes it back the way it was — so it never silently rewrites your line endings.
- Searches and reads documents, not just code. Word, Excel, PowerPoint, PDF and more are consumed automatically as Markdown, so you can point the agent at real-world documents alongside your source.
Features
- Multiple LLM providers: Anthropic, OpenAI, Google Vertex AI, Ollama, OpenRouter, SAP AI Core, Groq, Cerebras, Mistral, and more.
- Four ways to work: a native GUI (built on Zed's GPUI), a terminal mode, a headless MCP server, and an ACP agent for editors like Zed.
- Adaptive tool syntax: native function calling, XML tags, or triple-caret blocks — chosen per session to fit the model.
- Real-time streaming with smart filtering that blocks unsafe tool combinations (e.g. editing a file before reading it).
- Sessions per project with branching, persistent state, and draft messages with attachments.
- Sub-agents, permission tiers, a command sandbox, and automatic context compaction when the window fills up.
- MCP client mode: plug in external Model Context Protocol servers and use their tools.
- Browser sessions: the agent drives a real browser (navigate, read, click, type) to test web apps, with a human-in-the-loop login handoff so it acts as you without ever seeing your credentials.
- Skills: reusable, task-specific playbooks the agent can load on demand.
- Auto-loaded guidance: picks up
AGENTS.md(orCLAUDE.md) from your project root to align with repo-specific instructions.
Interfaces
code-assistant # native GUI (default)
code-assistant --tui # terminal interface
code-assistant acp # ACP agent for editors like Zed
code-assistant server # headless MCP server (e.g. Claude Desktop)
Any mode can take an initial task: code-assistant --task "Explain this codebase".
Add to your Zed settings:
{
"agent_servers": {
"Code-Assistant": {
"command": "/path/to/code-assistant",
"args": ["acp", "--model", "Claude Sonnet 4.5"],
"env": { "ANTHROPIC_API_KEY": "sk-ant-..." }
}
}
}
See Zed's docs on custom agents.
In Claude Desktop settings (Developer tab → Edit Config):
{
"mcpServers": {
"code-assistant": {
"command": "/path/to/code-assistant",
"args": ["server"],
"env": { "SHELL": "/bin/zsh" }
}
}
}
Configuration
For most people the in-app Settings screen is enough — it manages providers, models, MCP servers and skills for you. Everything can also be configured via JSON files, and there are more advanced options (project setup, sandbox modes, tool syntax, session recording, CLI flags):
→ See the Configuration guide.
Contributing
Contributions are welcome! The codebase is a decent tour of async Rust, AI agent architecture, and cross-platform UI. If something about the agent's behaviour annoys you, that is exactly the kind of detail this project cares about: please open an issue.
Roadmap
Not really a roadmap — just a few directions, in no particular order:
- Block replacing in stale files: detect early when the model is about to
replace_in_filea file that changed since it last read it, and reject with a helpful message. - Compact tool-use failures: strip failed tool calls / mismatched search blocks from the history to save tokens.
- Memory tools: help the agent build up a knowledge base for a project.
- Tighter sandboxing: restrict tool access to git-tracked files within the project.
- Fuzzy matching of search blocks: reduce the re-reads caused by failed exact matches.
Pertanyaan tentang Code Assistant MCP
Apa yang bisa dilakukan oleh Code Assistant MCP server?
Tool ini menjalankan headless MCP server yang memberikan AI client sebuah autonomous coding agent loop pada codebase Anda, mulai dari membaca, mencari, mengedit file, hingga menjalankan command.
Bagaimana cara menghubungkan Code Assistant ke Claude Desktop?
Tambahkan entry mcpServers yang mengarahkan command ke binary code-assistant dengan argumen 'server', dan Anda juga bisa mengatur environment variable SHELL jika diperlukan.
Provider LLM apa saja yang didukung oleh Code Assistant?
Tool ini mendukung Anthropic, OpenAI, Google Vertex AI, Ollama, OpenRouter, SAP AI Core, Groq, Cerebras, Mistral, dan lainnya.
Apakah Code Assistant bisa menggunakan MCP server eksternal?
Ya, tool ini memiliki mode MCP client sehingga Anda bisa menghubungkan external Model Context Protocol servers dan menggunakan tool yang mereka miliki.
Apakah Code Assistant berfungsi dengan editor seperti Zed?
Ya, tool ini menyediakan ACP agent yang bisa Anda daftarkan di settings agent_servers pada Zed.