Memberikan akses sandboxed dan berbasis kebijakan kepada AI coding agent ke repositori lokal untuk melakukan pencarian, pembacaan, patching, dan menjalankan command yang telah dikurasi.
Juga dikenal sebagai bgorzelic/ghostlink, @bgorzelic/ghostlink
- Stars
- 0
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- 0.1.0
- Commit terakhir
- 5 Okt 2026
- Lisensi
- ISC
Apa itu GhostLink MCP?
Memberikan akses sandboxed dan berbasis kebijakan kepada AI coding agent ke repositori lokal untuk melakukan pencarian, pembacaan, patching, dan menjalankan command yang telah dikurasi.
Ringkasan dibuat dari README proyek
Tentang GhostLink MCP server
GhostLink menyediakan lingkungan yang aman bagi AI coding agent untuk berinteraksi dengan codebase lokal. GhostLink berfungsi sebagai local-first Model Context Protocol server yang menggunakan transport STDIO untuk terhubung dengan client seperti Claude Code, Claude Desktop, Cursor, atau Windsurf. Dengan menetapkan repository root tertentu melalui environment variables, developer dapat memberikan akses terkontrol kepada agent untuk mencari, membaca, dan memodifikasi file tanpa mengekspos seluruh sistem terhadap shell command sembarangan.
Server ini menyertakan enam tool khusus yang dirancang untuk siklus coding otonom. Tool tersebut mencakup repo.search untuk pencarian regex menggunakan ripgrep, repo.read_file untuk membaca konten dengan batasan ukuran, dan repo.apply_patch untuk melakukan perubahan kode dengan kemampuan atomic rollback. GhostLink juga menawarkan repo.run untuk mengeksekusi allowlist command tertentu seperti test, lint, atau build, serta git.status dan git.diff untuk tugas version control. Setiap interaksi di-sandbox ke direktori yang ditentukan dan mengembalikan JSON envelope yang deterministik untuk perilaku agent yang dapat diprediksi.
Apa yang bisa Anda lakukan dengannya
- 1Auditing agent actionsTim dapat menyimpan jejak audit JSONL dari setiap pemanggilan tool untuk memantau bagaimana AI berinteraksi dengan kode.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal GhostLink MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal GhostLink MCP di Claude Code
$ claude mcp add --env 'GHOSTLINK_REPO_ROOT=<GHOSTLINK_REPO_ROOT>' ghostlink -- npx -y @bgorzelic/ghostlinkInstal GhostLink MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"ghostlink": {
"command": "npx",
"args": [
"-y",
"@bgorzelic/ghostlink"
],
"env": {
"GHOSTLINK_REPO_ROOT": "<GHOSTLINK_REPO_ROOT>"
}
}
}
}Instal GhostLink MCP di VS Code
.vscode/mcp.json
{
"servers": {
"ghostlink": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bgorzelic/ghostlink"
],
"env": {
"GHOSTLINK_REPO_ROOT": "<GHOSTLINK_REPO_ROOT>"
}
}
}
}Instal GhostLink MCP di VS Code CLI
$ code --add-mcp '{"name":"ghostlink","type":"stdio","command":"npx","args":["-y","@bgorzelic/ghostlink"],"env":{"GHOSTLINK_REPO_ROOT":"<GHOSTLINK_REPO_ROOT>"}}'Instal GhostLink MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"ghostlink": {
"command": "npx",
"args": [
"-y",
"@bgorzelic/ghostlink"
],
"env": {
"GHOSTLINK_REPO_ROOT": "<GHOSTLINK_REPO_ROOT>"
}
}
}
}Instal GhostLink MCP di Codex
$ codex mcp add ghostlink --env 'GHOSTLINK_REPO_ROOT=<GHOSTLINK_REPO_ROOT>' -- npx -y @bgorzelic/ghostlinkInstal GhostLink MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.ghostlink] command = "npx" args = ["-y", "@bgorzelic/ghostlink"] [mcp_servers.ghostlink.env] GHOSTLINK_REPO_ROOT = "<GHOSTLINK_REPO_ROOT>"
Instal GhostLink MCP di Gemini CLI
$ gemini mcp add -s user -e 'GHOSTLINK_REPO_ROOT=<GHOSTLINK_REPO_ROOT>' ghostlink npx -- -y @bgorzelic/ghostlinkInstal GhostLink MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"ghostlink": {
"command": "npx",
"args": [
"-y",
"@bgorzelic/ghostlink"
],
"env": {
"GHOSTLINK_REPO_ROOT": "<GHOSTLINK_REPO_ROOT>"
}
}
}
}Konfigurasi
GHOSTLINK_REPO_ROOTWajibAbsolute path to the repository the server is confined to. Every tool call is sandboxed beneath this path.
GHOSTLINK_LOGOptional path for the JSON audit log of tool calls. Omit to disable file logging.
| Nama | Deskripsi | Tipe |
|---|---|---|
| GHOSTLINK_REPO_ROOT | Absolute path to the repository the server is confined to. Every tool call is sandboxed beneath this path. | Wajib |
| GHOSTLINK_LOG | Optional path for the JSON audit log of tool calls. Omit to disable file logging. |
Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkaubgorzelic/ghostlink is public and reachablegithub.com/bgorzelic/ghostlink ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)ISCspdx.org/licenses/ISC.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-10-05github.com/bgorzelic/ghostlink ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from @bgorzelic/ghostlinkLolos
- Tidak ada advisory kritis pada paket atau dependensinyathe package checked; no critical advisoryosv.dev ↗Lolos
- 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 GitHubGhostLink
A security-hardened MCP server that gives AI coding agents safe, deterministic access to local repositories.
Add it to any MCP client that supports STDIO. For Claude Code, create .mcp.json in the target repo root:
{
"mcpServers": {
"ghostlink": {
"command": "npx",
"args": ["-y", "ghostlink"],
"env": {
"GHOSTLINK_REPO_ROOT": "/path/to/target/repo"
}
}
}
}
Then run claude in that directory — six repo tools appear, all confined to GHOSTLINK_REPO_ROOT. Every tool call returns the same deterministic ToolEnvelope:
{
"ok": true,
"data": { ... },
"provenance": { "tool": "repo.search", "timestamp": "2026-02-24T...", "duration_ms": 42 }
}
On error, "error": { "code": "...", "message": "..." } replaces "data". Full tool schemas: docs/TOOLS.md.
Tools
| Tool | Description |
|---|---|
repo.search |
Ripgrep-powered regex search with glob filtering, deterministic ordering, and output caps (max 200 results) |
repo.read_file |
File read with size caps (max 10MB), binary detection, and truncation flags |
repo.apply_patch |
Unified diff patching with dry-run mode, full sandbox validation, and atomic rollback on failure |
repo.run |
Curated command execution (test, lint, typecheck, build, smoke) -- no arbitrary shell, allowlisted args only |
git.status |
Normalized git status with branch info, ahead/behind tracking, and sorted file entries |
git.diff |
Staged or unstaged diff with path filtering, sandbox validation, and output caps (max 2MB) |
What is GhostLink?
GhostLink is a local-first Model Context Protocol server that exposes your codebase to AI coding agents through a small set of policy-gated tools. It solves a specific problem: AI agents need to search, read, patch, and verify code, but giving them raw shell access is a liability. GhostLink provides a sandboxed capability plane where every tool call is confined to a single repository root, every output follows a deterministic JSON shape, and every invocation is audit-logged.
Why GhostLink?
| Capability | What it means |
|---|---|
| Secure local dev plane | Repo-root sandbox, no shell execution, JSONL audit trail on every tool call |
| Deterministic output | Same input produces the same JSON envelope shape -- enables golden tests and predictable agent consumption |
| Policy enforcement | Command allowlists, output caps, truncation flags, timeout enforcement -- the AI cannot do unbounded damage |
| Agent loop foundation | Built for the search, read, patch, verify cycle that autonomous coding agents run in a loop |
| Multi-server composition | One GhostLink instance per repo, composable with other MCP servers in the same client session |
| Production-ready Phase 2 base | Transport abstraction, schema versioning, and auth hook seams are preserved in the architecture today |
Architecture
GhostLink is a three-layer stack designed for extensibility without core changes:
flowchart TD
T["Transport -- src/index.ts<br/>STDIO now, HTTP/SSE in Phase 2"]
S["Server factory -- src/server.ts<br/>Transport-agnostic tool registration via MCP SDK + Zod schemas"]
TL["Tools -- src/core/tools/*<br/>Six tools, each returning ToolEnvelope<T>"]
P["Policy -- src/core/policy/*<br/>Sandbox enforcement, audit logging, output caps"]
T --> S --> TL --> P
The createServer() factory knows nothing about transport. Adding HTTP/SSE in Phase 2 means writing a new transport binding and auth middleware -- the server factory and all tool implementations remain unchanged. Phase 3 (agent runtime) adds memory resources and orchestration as consumers of GhostLink, not modifications to it.
Quick Start
Prerequisites
- Node.js 18+
- ripgrep (
brew install ripgrep) - A git repository to expose
Install
From npm:
npm install ghostlink
Or from source:
git clone https://github.com/bgorzelic/ghostlink.git
cd ghostlink
npm install
npm run build
Smoke Test (Raw STDIO)
GhostLink speaks JSON-RPC 2.0 over STDIO. Test it directly:
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | \
GHOSTLINK_REPO_ROOT=/path/to/target/repo node dist/index.js
This returns all 6 tools and their schemas.
Client Configuration
GhostLink works with any MCP client that supports STDIO transport. The npx snippet at the top of this page works everywhere; a source checkout uses node with the built entry point instead:
{
"ghostlink": {
"command": "node",
"args": ["/absolute/path/to/ghostlink/dist/index.js"],
"env": {
"GHOSTLINK_REPO_ROOT": "/path/to/target/repo"
}
}
}
| Client | Where the config goes |
|---|---|
| Claude Code | .mcp.json in the target repo root (mcpServers key), then run claude there |
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json (mcpServers key), then restart |
| Cursor, Windsurf, Cline, others | Your client's MCP server configuration -- consult its documentation for the file location |
The transport is always STDIO. Ready-to-use .mcp.json and CLAUDE.md templates for target projects live in templates/.
Security Model
GhostLink enforces defense-in-depth at every layer:
- Repo-root sandbox -- All file operations confined to
GHOSTLINK_REPO_ROOT. Path traversal, symlink escape, null bytes, and absolute paths outside the root are all rejected before any filesystem access. - No shell execution --
repo.runusesspawnwithshell: false. Commands are limited to a fixed allowlist (test, lint, typecheck, build, smoke) with per-command argument allowlists. Environment is stripped to six safe variables. - Output caps -- Every tool that returns bulk data enforces hard maximums (200 search results, 10MB file reads, 200KB stdout/stderr, 2MB diffs). Truncation is flagged, never silent.
- Atomic patch rollback --
repo.apply_patchvalidates all paths and computes all patches before writing anything. If any write fails, completed writes are rolled back to their original state. - Timeout enforcement --
repo.runkills processes at configurable timeouts (default 120s, hard cap 300s) with SIGTERM then SIGKILL.
Full threat model and mitigations: docs/SECURITY.md.
Audit Logging
Every tool call produces a JSONL audit entry: {ts, tool, ok, duration_ms, error_code?, repo_root}.
GHOSTLINK_LOG |
Behavior |
|---|---|
stdout (default) |
JSONL audit lines written to stderr |
file |
JSONL written to logs/ghostlink.jsonl (auto-rotates at 10MB) |
off |
No logging |
Set via environment variable:
GHOSTLINK_LOG=file GHOSTLINK_REPO_ROOT=/path/to/repo node dist/index.js
Prompt Templates
docs/PROMPTS.md contains ready-to-use prompts for high-autonomy agent operation, including orchestrator prompts, sub-agent role definitions (Protocol Engineer, Toolsmith, Security Reviewer, Test Engineer, Docs Engineer), and multi-instance coordination patterns.
Development
npm install # Install dependencies
npm test # Run test suite (108 tests via Vitest)
npm run lint # ESLint
npm run typecheck # TypeScript strict mode check
npm run build # Compile to dist/
npm run dev # Dev mode with auto-reload (tsx watch)
Full verification after edits:
npm test && npm run lint && npm run typecheck && npm run build
Documentation
| Document | Description |
|---|---|
| docs/TOOLS.md | Canonical tool schemas (versioned public API) |
| docs/SECURITY.md | Threat model and mitigations |
| docs/QUICKSTART.md | Setup, smoke tests, and client configuration walkthrough |
| docs/INSPECTOR.md | MCP Inspector manual testing guide |
| docs/PROMPTS.md | Agent prompts for orchestration and sub-agent roles |
| docs/ROADMAP_DETAILED.md | Full product roadmap with Phase 2 and Phase 3 deliverables |
| docs/WHY_GHOSTLINK.md | Strategic value proposition and architecture rationale |
| docs/ENGINEERING_REPORT_v0.1.0.md | v0.1.0 ship report with milestone history and decision log |
| templates/ | Ready-to-use CLAUDE.md and .mcp.json templates for target projects |
Roadmap
Phase 1 -- Local STDIO [Shipped, v0.1.0]
Deterministic tool surface, repo-root sandbox, curated command execution, 108 tests, JSONL audit logging, npm package published.
Phase 2 -- Remote Transport [Planned]
HTTP/SSE transport, OAuth 2.1 authentication, multi-user tenant separation, per-tenant rate limiting, schema versioning, structured audit logging with correlation IDs.
Phase 3 -- Agent Runtime [Future]
Persistent memory resources exposed via MCP, optional policy-gated memory write tools, orchestration layer (external to GhostLink), evaluation loops, sub-agent coordination framework.
License
ISC
Pertanyaan tentang GhostLink MCP
Bagaimana cara menambahkan GhostLink MCP ke Claude Code?
Jalankan claude mcp add --env 'GHOSTLINK_REPO_ROOT=<GHOSTLINK_REPO_ROOT>' ghostlink -- npx -y @bgorzelic/ghostlink di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan GhostLink MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Bagaimana cara mengonfigurasi GhostLink untuk Claude Code?
Buat file .mcp.json di root repositori target Anda yang berisi command ghostlink dan environment variable GHOSTLINK_REPO_ROOT.
Apakah aman memberikan akses file saya kepada AI agent menggunakan GhostLink?
Ya, GhostLink menggunakan sandbox repo-root yang menolak path traversal dan symlink escapes, serta mencegah eksekusi shell sembarangan dengan menggunakan allowlist command.
Apa yang terjadi jika file patch gagal?
Server akan melakukan atomic rollback untuk mengembalikan file ke kondisi semula jika ada bagian dari operasi penulisan yang gagal.
Bisakah saya melihat log dari apa yang telah dilakukan AI agent?
Ya, setiap tool call menghasilkan entri audit JSONL yang dapat dikirim ke stdout atau ke sebuah file.