CacheBash MCP server
Commit 13 Nov 2026Memungkinkan koordinasi multi-agent melalui dispatching tugas, relay messaging, persistent memory, dan persetujuan mobile via human-in-the-loop.
Juga dikenal sebagai rezzedai/cachebash
- Stars
- 0
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- 2.0.0
- Commit terakhir
- 13 Nov 2026
- Lisensi
- MIT
Apa itu CacheBash MCP?
CacheBash adalah MCP server. Memungkinkan koordinasi multi-agent melalui dispatching tugas, relay messaging, persistent memory, dan persetujuan mobile via human-in-the-loop.
Ringkasan dibuat dari README proyek
Tentang CacheBash MCP server
CacheBash menyediakan layer koordinasi untuk sistem multi-agent menggunakan Model Context Protocol. Ini memungkinkan berbagai agent untuk berkomunikasi, melakukan hand-off tugas, dan mempertahankan persistent memory di berbagai sesi. Developer dapat men-deploy server ini di Cloud Run atau host Node.js lainnya, dengan memanfaatkan Google Cloud Firestore untuk penyimpanan data yang terisolasi. Sistem ini mendukung berbagai client termasuk Claude Code, Cursor, VS Code dengan Copilot, dan Gemini CLI melalui streamable HTTP.
Platform ini memiliki 108 tools yang terorganisir ke dalam 21 domain, seperti dispatch, relay, dan state. Sistem ini mengelola seluruh lifecycle tugas melalui tools untuk membuat, mengklaim, dan menyelesaikan pekerjaan, sambil memastikan dua agent tidak dapat mengklaim tugas yang sama melalui transaksi Firestore. Keamanan ditangani melalui API key dengan scope capability yang memfilter daftar tool yang tersedia. Aspek unik dari server ini adalah kemampuan human-in-the-loop, yang menggunakan aplikasi mobile React Native untuk memungkinkan Anda menyetujui permintaan atau menjawab pertanyaan langsung dari ponsel.
Apa yang bisa Anda lakukan dengannya
- 1Koordinasi handoff tugas multi-agentBerikan bagian pekerjaan tertentu ke agent lain dan pantau progresnya melalui seluruh lifecycle.
- 2Implementasi persetujuan human-in-the-loopHentikan sementara workflow agent otonom untuk menunggu pengguna menyetujui sebuah keputusan melalui perangkat mobile.
- 3Mempertahankan memori agent jangka panjangPastikan agent mengingat pola yang telah dipelajari dan riwayat konteks di berbagai sesi yang berbeda.
- 4Menerapkan izin tool yang granularBatasi akses agent ke fungsi spesifik seperti membaca atau menulis pesan menggunakan scoped keys.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal CacheBash MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal CacheBash MCP di Claude Code
$ claude mcp add --transport http cachebash https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcpInstal CacheBash MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"cachebash": {
"url": "https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcp"
}
}
}Instal CacheBash MCP di VS Code
.vscode/mcp.json
{
"servers": {
"cachebash": {
"type": "http",
"url": "https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcp"
}
}
}Instal CacheBash MCP di VS Code CLI
$ code --add-mcp '{"name":"cachebash","type":"http","url":"https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcp"}'Instal CacheBash MCP di Codex
$ codex mcp add cachebash --url https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcpInstal CacheBash MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.cachebash] url = "https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcp"
Instal CacheBash MCP di Gemini CLI
$ gemini mcp add -s user --transport http cachebash https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcpInstal CacheBash MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"cachebash": {
"url": "https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcp",
"type": "http"
}
}
}Pengecekan otomatis
Berjalan 15 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 dijangkaurezzedai/cachebash is public and reachablegithub.com/rezzedai/cachebash ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-13github.com/rezzedai/cachebash ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- 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 MCPHTTPS endpoint answered 401 (sign-in required)Lolos
README
Lihat di GitHubCacheBash
CacheBash is an open-source MCP server for multi-agent coordination. It is written in TypeScript and works with any model and any MCP client. Agents use it to hand work to each other, message each other, report their state and ask a human for decisions. The human answers from a phone.
Architecture at a glance
- 108 MCP tools in 21 domains. The default deployment profile serves 107 of them. A smaller "lite" profile for tenant deployments serves 96.
- Task dispatch. Agents create, claim and complete tasks. Claims run inside a Firestore transaction, so two agents cannot claim the same task.
- Relay messaging. Direct messages, group multicast and message history. Messages that cannot be delivered go to a dead-letter queue for inspection.
- Human in the loop. Agents send questions and approval requests. The mobile app shows them, and the agent continues when the human answers.
- Capability-scoped keys. Each API key carries capabilities such as
dispatch.readorrelay.write. The tool list a client sees is filtered to that key's capabilities, and every call is checked again. - Policy checks before dispatch. The dispatch pre-flight evaluates the configured policies before a task is created.
- Per-task telemetry. Task completion records the status, model, provider, input and output tokens, cost, and a failure class.
- Persistent agent memory. Each program keeps state, learned patterns and memories across sessions.
How it runs:
- Server: TypeScript on Cloud Run, or any Node.js host.
- Storage: Google Cloud Firestore, with data isolated per user.
- Auth: Firebase Auth (GitHub and Google sign-in) plus per-program API keys.
- Mobile: React Native and Expo, for iOS and Android.
- Transport: MCP Streamable HTTP with Bearer token auth.
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Claude Code │ │ Cursor │ │ VS Code │
└──────┬──────┘ └──────┬──────┘ └──────┬──────┘
└────────────────┼────────────────┘
│ MCP (Streamable HTTP)
▼
┌───────────────────┐
│ CacheBash server │
│ (Cloud Run) │
└─────────┬─────────┘
┌───────┴────────┐
▼ ▼
┌────────────┐ ┌────────────┐
│ Firestore │ │ Mobile app │
└────────────┘ └────────────┘
Supported clients
| Client | Status |
|---|---|
| Claude Code | Supported |
| Cursor | Supported |
| VS Code + Copilot | Supported |
| Gemini CLI | Supported |
| Any MCP-compatible client | Supported |
CacheBash uses the standard MCP protocol. No orchestration logic depends on one vendor's SDK.
Tool domains
Counts come from the tool definitions in services/mcp-server/src/tools/. Most tools are named <domain>_<action>.
| Domain | Tools | What it does |
|---|---|---|
| dispatch | 24 | Task lifecycle: create, claim, complete, approve, retry, reassign, escalate, lineage, telemetry |
| gsp | 9 | Grid State Protocol: bootstrap, read, write, search, diff, propose and resolve shared state |
| pulse | 9 | Sessions and fleet health: create, update, list, pause, resume, timeline, snapshots |
| metrics | 8 | Cost summary and forecast, operational and comms metrics, SLA compliance, rate-limit events |
| state | 8 | Per-program state and memory: store, recall, reinforce, delete, context history |
| relay | 7 | Messages, directives, groups, history and dead letters |
| policy | 6 | Create, read, update, delete, list and check policies |
| schedule | 5 | Recurring and one-off scheduled work |
| sprint | 5 | Sprints with stories, dependencies and wave-based execution |
| keys | 4 | API key create, list, revoke and rotate |
| webhook | 4 | Register, list and delete webhooks, and read delivery logs |
| clu | 3 | Ingest, analyze and report on transcripts |
| signal | 3 | Push alerts and questions to the mobile app, and read the answers |
| audit | 2 | Audit log and acknowledgement compliance |
| dream | 2 | Overnight autonomous runs with budget caps |
| pattern | 2 | Consolidate learned patterns across programs |
| programs | 2 | List and update registered programs |
| trace | 2 | Query request traces |
| admin | 1 | Account administration |
| feedback | 1 | Submit feedback |
| request_help | 1 | Cross-grid help requests (lite profile only) |
| Total | 108 |
API reference: docs/api-reference.md and docs.rezzed.ai
Quick start
Hosted
# 1. Install and authenticate
npx cachebash init
# 2. Verify connection
cachebash ping
# 3. Open the mobile app. Your agent appears.
npx cachebash init signs you in through the browser and writes the MCP config for Claude Code, Cursor or VS Code.
Self-hosted
# 1. Clone the repo
git clone https://github.com/rezzedai/cachebash.git
cd cachebash
# 2. Install dependencies
cd services/mcp-server && npm install
# 3. Set up Firebase
# Create a Firebase project and enable Firestore.
# Download a service account key and set GOOGLE_APPLICATION_CREDENTIALS.
# 4. Configure environment
cp .env.example .env
# Edit .env with your Firebase project details
# 5. Start the server
npm start
# 6. Configure your MCP client
# Add to your Claude Code / Cursor MCP config:
{
"mcpServers": {
"cachebash": {
"url": "http://localhost:3000/v1/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Set CACHEBASH_PROFILE=lite to serve the smaller tool set. The profile logic is in services/mcp-server/src/tools/index.ts. Deployment notes: docs/deployment.md.
Project structure
cachebash/
├── apps/
│ └── mobile/ # Mobile app (React Native + Expo)
├── services/
│ ├── mcp-server/ # MCP server (TypeScript, Cloud Run)
│ └── functions/ # Cloud Functions (auth, notifications, cleanup)
├── packages/
│ ├── cli/ # CLI tool (npx cachebash)
│ └── types/ # Shared TypeScript types
├── infra/ # Firebase rules and indexes
├── docs/ # Documentation
├── turbo.json # Turborepo build orchestration
└── package.json # npm workspaces root
More detail: docs/architecture.md
Contributing
The CacheBash MCP server is MIT licensed. Contributions are welcome.
git clone https://github.com/rezzedai/cachebash.git
cd cachebash
npm install # installs all workspaces
npm run dev
See CONTRIBUTING.md for guidelines.
Links
License
MIT. See LICENSE.
Built by Rezzed.ai
Pertanyaan tentang CacheBash MCP
Bagaimana cara menambahkan CacheBash MCP ke Claude Code?
Jalankan claude mcp add --transport http cachebash https://cachebash-mcp-922749444863.us-central1.run.app/v1/mcp di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan CacheBash 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 agent berinteraksi dengan manusia?
Agent dapat mengirimkan pertanyaan dan permintaan persetujuan yang akan muncul di aplikasi mobile, sehingga Anda dapat memberikan jawaban agar agent bisa melanjutkan tugasnya.
Apakah beberapa agent bisa mengambil tugas yang sama?
Tidak, proses klaim diproses di dalam transaksi Firestore untuk memastikan tidak ada dua agent yang dapat mengambil tugas yang sama secara bersamaan.
Apakah mendukung persistent memory?
Ya, setiap program mempertahankan state, pola yang dipelajari, dan memori di berbagai sesi yang berbeda.