by productdevbook
Unified inbox that aggregates email, live‑chat, in‑app conversations, newsletters, analytics, status pages, help center articles, roadmaps and changelogs into a single self‑hosted platform.
Yuva provides a single shared inbox for every product a team runs. It consolidates customer communications across email, live‑chat widgets, in‑app messages and feedback, while also offering tools for newsletters, help‑center publishing, status pages, product roadmaps, and cookieless web analytics. The platform is open‑source, self‑hosted (Docker + PostgreSQL), and includes an MCP endpoint for AI‑assistant integration.
compose.yaml and .env (see the quick‑start guide) and run docker compose up -d.docker compose exec yuva /yuva bootstrap --email you@example.com --workspace "Example"./mcp endpoint to connect AI assistants, widgets, or other services.oci://ghcr.io/productdevbook/charts/yuva).npm install useyuva), React shadcn/ui components, iOS/macOS Swift package, Android Maven artifact, and Go SDK./mcp endpoint) or use the bundled yuva.mcpb binary from a release; then configure assistants with OAuth credentials.One inbox for every product you run.
Website · Docs · API · Releases · Roadmap · X
Yuva is open-source customer messaging for teams that run several products. Support e-mail, live chat, in-app messages and feedback from every product land in one shared inbox, next to the newsletters, help center, status pages and analytics you send and publish from the same place.
You host it yourself: one Docker image and Postgres.
[!WARNING] Beta. The API can still change before 1.0, so read the release notes before you upgrade. Database migrations run when the server starts: back up first. The code has not had an independent security audit.
| Conversations | One inbox per product with its own branding, language, hours and team. E-mail, live chat, in-app messages and app feedback in one thread, with notes, labels, mentions and bot drafts a member reviews. |
| Reach | Mailing lists with consent records and imports, e-mail designs from templates, broadcasts with approval and reports, and a deliverability check. |
| Publish | Help center, documentation pages, status pages on your own domain, a roadmap board and What's new. |
| Insights | Cookieless analytics for websites and apps, and a support report that ranks pages by the conversations they cause. |
| Move in | Migrations of history and live mail from Gmail, Microsoft 365, Yandex, iCloud, Zoho, any IMAP server, Zendesk and Help Scout. The old mailbox is only read. |
| Build on it | A REST API with scoped keys, signed webhooks, identity tokens, headless mode, and an MCP server with OAuth for Claude, Cursor, VS Code and other assistants. |
Built with Go, Postgres and a React panel, shipped as one Docker image.
Write compose.yaml and .env from the install guide.
Start it:
docker compose up -d
Create the first owner:
docker compose exec yuva /yuva bootstrap --email you@example.com --workspace "Example"
Put it behind HTTPS and sign in with the code that arrives by e-mail.
On Kubernetes, install the Helm chart oci://ghcr.io/productdevbook/charts/yuva; see
Kubernetes with Helm.
| For | Install | Guide |
|---|---|---|
Web: <yuva-chat>, headless client |
npm install useyuva |
Web widget, Headless |
| React and shadcn/ui | npx shadcn@latest add https://useyuva.com/r/yuva-discussions.json |
shadcn registry |
| iOS and macOS | Swift package https://github.com/productdevbook/yuva.git, product YuvaKit |
Mobile SDKs |
| Android | implementation("com.github.productdevbook:yuva:v0.0.32") |
Mobile SDKs |
| Go | go get github.com/productdevbook/yuva/sdk/go |
Go SDK |
| AI assistants | /mcp on your server, or yuva.mcpb from a release |
MCP |
Working projects are in examples.
Guides, the API reference and examples are at useyuva.com/docs, and in docs/ (also in Turkish and German). How it is built: architecture. What is next: roadmap. What changed: GitHub Releases.
Read CONTRIBUTING.md first; contributions are made under the CLA.
For a local server with Postgres and Mailpit, which catches every mail it sends, run
docker compose -f deploy/compose.yaml up -d.
Ask questions and report bugs in issues, and follow
@useyuva for news.
The server and panel are AGPL-3.0. The SDKs (sdk/) and the API contract (openapi/)
are MIT, so you can ship them in closed-source apps. Details in
LICENSING.md; name and logo in TRADEMARK.md.
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by activepieces
A self‑hosted, open‑source platform that provides a no‑code builder for creating, versioning, and running AI‑driven automation workflows. Pieces are TypeScript‑based plugins that become MCP servers, allowing direct consumption by large language models.
by Skyvern-AI
Automates browser‑based workflows by leveraging large language models and computer‑vision techniques, turning natural‑language prompts into fully functional web interactions without writing custom scripts.
by rocketride-org
Build, debug, and scale LLM workflows with a high‑performance C++ core and over 50 extensible Python nodes, supporting multiple model providers, vector databases, and agent orchestration, all from within your IDE.
by ahujasid
Enables Claude AI to control Blender for prompt‑assisted 3D modeling, scene creation, and manipulation via a socket‑based Model Context Protocol server.
by PipedreamHQ
Connect APIs quickly with a free, hosted integration platform that enables event‑driven automations across 1,000+ services and supports custom code in Node.js, Python, Go, or Bash.
by elie222
Organizes email inbox, drafts replies in the user's tone, tracks follow‑ups, and provides analytics to achieve inbox zero quickly.
by grab
Enables Cursor AI to read and programmatically modify Figma designs through a Model Context Protocol integration.
by CursorTouch
Enables AI agents to control the Windows operating system, performing file navigation, application launching, UI interaction, QA testing, and other automation tasks through a lightweight server.
by ahujasid
Enables Claude AI to control Ableton Live in real time, allowing AI‑driven creation, editing, and playback of tracks, clips, instruments, and effects through a socket‑based server.