Biarkan AI coding agent memeriksa struktur repository, mencari kode, dan mengingat konvensi proyek melalui MCP dan CLI.
Juga dikenal sebagai PatrickSys/codebase-context
- Stars
- 68
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 7 Nov 2026
- Lisensi
- —
Apa itu Codebase Context MCP?
Codebase Context adalah MCP server. Biarkan AI coding agent memeriksa struktur repository, mencari kode, dan mengingat konvensi proyek melalui MCP dan CLI.
Ringkasan dibuat dari README proyek
Tentang Codebase Context MCP server
Membantu AI coding agent memahami repository yang kompleks adalah tujuan utama codebase-context melalui tool indexing dan retrieval khusus. Developer menggunakan tool ini untuk memberikan repository map tingkat tinggi, referensi symbol, dan hubungan antar file kepada agent, sehingga memungkinkan AI untuk memeriksa struktur proyek sebelum mencoba melakukan perubahan apa pun. Tool ini bekerja secara lokal melalui stdio atau melalui setup HTTP tingkat lanjut, dan dapat diinisialisasi untuk client spesifik seperti Claude Code, Cursor, Codex, dan OpenCode.
Pengguna dapat memilih antara index berbasis keyword default yang tidak memerlukan API key atau GPU, atau mode semantic indexing opsional yang menggunakan embedding providers. Sistem ini menyertakan fitur unik seperti project memory untuk menyimpan konvensi dan tool review context yang membuat paket terbatas dari Git diffs. Meskipun keyword index dibatasi hingga 5.000 chunk yang dapat dicari secara default, pengguna dapat menyesuaikan batasan ini melalui konfigurasi. Tool ini menyediakan analyzer khusus untuk framework seperti React, Next.js, Angular, dan NestJS untuk meningkatkan cara agent menavigasi codebase.
Apa yang bisa Anda lakukan dengannya
- 1Memetakan struktur repositoryMinta AI agent untuk menghasilkan gambaran umum tingkat tinggi tentang organisasi dan pola proyek sebelum memulai sebuah tugas.
- 2Mencari kode spesifikArahkan AI untuk menemukan symbol atau fitur spesifik di dalam codebase menggunakan hasil pencarian terperingkat.
- 3Mengingat konvensi proyekInstruksikan agent untuk mengambil keputusan atau aturan arsitektur yang telah disimpan sebelumnya menggunakan tool memory.
- 4Menganalisis perubahan terbaruBerikan AI context yang diperlukan dari commit terbaru untuk melakukan code review yang terfokus.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal Codebase Context MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal Codebase Context MCP di Claude Code
$ claude mcp add codebase-context -- npx -y codebase-contextInstal Codebase Context MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"codebase-context": {
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Instal Codebase Context MCP di VS Code
.vscode/mcp.json
{
"servers": {
"codebase-context": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Instal Codebase Context MCP di VS Code CLI
$ code --add-mcp '{"name":"codebase-context","type":"stdio","command":"npx","args":["-y","codebase-context"]}'Instal Codebase Context MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"codebase-context": {
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Instal Codebase Context MCP di Codex
$ codex mcp add codebase-context -- npx -y codebase-contextInstal Codebase Context MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.codebase-context] command = "npx" args = ["-y", "codebase-context"]
Instal Codebase Context MCP di Gemini CLI
$ gemini mcp add -s user codebase-context npx -- -y codebase-contextInstal Codebase Context MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"codebase-context": {
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Pengecekan otomatis
Berjalan 13 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkaupatricksys/codebase-context is public and reachablegithub.com/patricksys/codebase-context ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyacodebase-context names patricksys/codebase-context as sourcenpmjs.com/package/codebase-context ↗Lolos
- Provenance build (atestasi Sigstore)Sigstore attestation for codebase-contextnpmjs.com/package/codebase-context/v/2.2.0#provenance ↗Lolos
- Lisensi open source (OSI)No licenseTemuan
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-07github.com/patricksys/codebase-context ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from codebase-contextLolos
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubCodebase Context
Local repository maps, code search and symbol references for coding agents. Codebase Context exposes these through MCP and a CLI so an agent can inspect the repository before editing it.
Published beta: 2.3.1-beta.0 (stable: 2.2.0)
As checked on 4 November 2026, npm beta points to 2.3.1-beta.0, while npm latest remains 2.2.0. The beta requires Node.js 22 or newer. An unpinned npx -y codebase-context may use an already installed local version; without one, it resolves npm latest (currently the stable 2.2.0). To select the published beta explicitly, use npx -y codebase-context@2.3.1-beta.0 --version. A source checkout or a local tarball is separate from a verified registry release.
Fresh beta indexes use keyword search without downloading an embedding or reranker model. Existing indexes keep their recorded mode. Semantic indexing is an explicit option; its optional runtimes and model downloads are separate from the default path.
Try the beta or a local build from the terminal
Use an explicitly installed 2.3.1-beta.0, a built checkout (pnpm install, then pnpm build in the CBC checkout) or an installed local tarball. From the repository you want to inspect, point Node at that installation's actual entrypoint:
node /path/to/codebase-context/dist/index.js --version
node /path/to/codebase-context/dist/index.js map
node /path/to/codebase-context/dist/index.js search --query "a symbol or feature in this repository" --limit 5
node /path/to/codebase-context/dist/index.js status
Replace the paths and query with your own. For a tarball installed under /path/to/cbc-local, the entrypoint is /path/to/cbc-local/node_modules/codebase-context/dist/index.js. Quote paths containing spaces.
map builds an index when the folder has no previous index. It then returns a bounded repository map. Search returns ranked source locations; open the returned code before relying on it. Low confidence means weak matching evidence, not that an implementation is absent.
To refresh the index, use reindex. Omitting mode flags preserves the recorded mode; reindex --no-embeddings explicitly selects keyword-only indexing. reindex --embeddings selects the configured embedding provider and requires optional LanceDB storage. The default local provider also requires Transformers and may download models; an explicitly configured remote provider has its own connection requirements. Changing modes requires a full rebuild, including when --incremental is supplied.
Set up your AI client
From the target repository, the installed beta or built source can write project registrations for selected detected clients:
node /path/to/codebase-context/dist/index.js init
# Or select one client explicitly:
node /path/to/codebase-context/dist/index.js init --client codex --root /path/to/project --yes
The wizard recognizes Claude Code, Codex, Cursor and OpenCode. It saves the Node binary and package entrypoint that ran setup. If that installation or its npx cache is moved or removed, rerun setup. Writing a config does not prove that a native client connected or completed a coding task.
After registration, restart the client and ask:
Use Codebase Context to find [feature] in this repository. Pass this repository's absolute path as project, wait for indexing if needed, and open the relevant source files.
The client setup guide contains beta setup instructions and dated checks for the older stable package. Historical manual recipes, including Windsurf, retain their dated verification limits. For example, the following manual registration leaves the package version unpinned; it may use an already installed local version or fall back to npm latest, so it does not reliably select the beta:
claude mcp add --scope user --transport stdio codebase-context -- npx -y codebase-context
The default transport is stdio: the client starts the server. HTTP is an advanced option with client-specific setup. Explicit project selection is the portable default. A successful selection becomes active for later calls in that server process; select again after restarting or changing repositories.
What your agent can inspect
- Repository map: structure, detected patterns and example files before narrowing to a task.
- Code search: bounded, ranked results with source locations and search-quality information. The default compact response contains at most six results.
- Symbol references: static identifier occurrences. They are not a runtime call graph.
- File relationships: TypeScript/JavaScript imports and re-exports, with unresolved or stale edges reported. Python and Go import navigation are not supported.
- Team patterns: file-level frequencies and example files. These are observations about the repository, not prescriptions about code quality.
- Project memory:
rememberandget_memorystore and retrieve project conventions, decisions, gotchas and failures. - Review context:
codebase-context-reviewbuilds a bounded packet from a committed Git diff. It does not review code or establish reviewer quality. The review-context guide retains a separate historical version preview; it is not evidence of this candidate's publication.
Dedicated analyzers in the source cover Angular, React, Next.js and NestJS. Other files use the generic analyzer and available parsers. See the capabilities reference for scope and limitations.
Privacy and storage
The default keyword index is built locally. Docker, a GPU and an API key are not required. Optional local embeddings also run on the machine. If you explicitly configure a remote embedding provider, code chunks are sent to that provider.
Your AI client may send returned code to its own model provider; CBC does not control that connection. Project memory also travels with the repository if you commit and push it.
Generated index data should stay out of version control. To share project memory while ignoring the generated index:
.codebase-context/*
!.codebase-context/memory.json
Evidence and limits
The benchmark report and prior report archive describe separate historical experiments. These are retrieval observations, not a winner or a coding-quality claim. This historical evidence does not establish patch correctness or end-to-end coding quality. Versions, fixtures and failure records matter; these reports do not certify this candidate. This draft makes no claim that CBC beats text search, improves coding outcomes, or reduces time or tokens.
The default keyword path can miss natural-language questions when their vocabulary differs from the code. A returned file and a high score are not proof that an answer is correct. Inspect the cited implementation. Optional semantic search has not established a retrieval-quality advantage for this candidate.
Other practical limits:
- The default keyword index holds at most 5,000 searchable chunks per project.
projects[].parsing.maxChunkscan raise that limit. - Search has bounded candidate inspection. Narrow a query when the candidate budget is exhausted; refresh when source files changed or became unavailable.
- Existing formats or incomplete generations can require an explicit rebuild or recovery choice. A failed operation is not a successful recovery.
- Setup evidence differs by client. Config writing, protocol connectivity and native-client task completion are separate checks.
- Stdio routing checks do not establish concurrent HTTP client isolation.
Reference
- Client setup — candidate registration, dated checks and limits
- Capabilities — tools, routing, configuration and optional modes
- CLI — local-candidate commands and historical illustrations
- Benchmark — historical methods, observations and failures
- Contributing — local development and evaluation commands
- Changelog — candidate changes and historical entries
Elastic-2.0. See LICENSE.
Pertanyaan tentang Codebase Context MCP
Bagaimana cara menambahkan Codebase Context MCP ke Claude Code?
Jalankan claude mcp add codebase-context -- npx -y codebase-context di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan Codebase Context MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Apa yang bisa diperiksa oleh AI agent dengan Codebase Context?
Agent dapat melihat repository map, menjalankan pencarian kode terperingkat, mencari referensi symbol dan hubungan antar file, mengamati pola tim, serta menyimpan atau mengambil project memory.
Apakah Codebase Context memerlukan Docker, GPU, atau API key?
Tidak. Keyword index bawaan dibangun secara lokal tanpa Docker, GPU, atau API key. Embeddings opsional juga berjalan secara lokal kecuali jika Anda secara eksplisit mengonfigurasi remote provider.
Client AI mana saja yang bisa dikonfigurasi secara otomatis oleh Codebase Context?
Init wizard dapat mengenali Claude Code, Codex, Cursor, dan OpenCode serta menulis registrasi proyek untuk mereka.
Berapa banyak hasil yang dikembalikan oleh pencarian kode default?
Respon compact search default berisi maksimal enam hasil terperingkat.
Apakah data index yang dihasilkan harus di-commit ke version control?
Tidak. Anda sebaiknya tidak memasukkan data index yang dihasilkan ke dalam version control dan secara opsional hanya perlu melakukan commit pada file project memory saja.