Turjuman
Supports reading and writing Android localization files (strings.xml) for translation management.
Supports reading and writing Flutter ARB localization files for translation management.
Supports reading and writing iOS localization files (.strings and .stringsdict) for translation management.
Supports reading and writing YAML localization files for translation management.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Turjumanadd a French locale for the checkout project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Turjuman
Open-source, self-hosted translation management — managed by your AI agent.
Turjuman is a lightweight, open-source alternative to commercial translation-management SaaS. Instead of a heavy web dashboard, you manage projects, keys, locales and translations through an MCP server connected to Claude Code (or any MCP client/agent). A thin developer CLI handles the deterministic file work — pulling/pushing locale files in your repo and CI.
It runs on a serverless AWS stack (Lambda + DynamoDB) that costs ~nothing to host and fits comfortably in the free tier. No always-on servers, no Cognito.
Claude Code / agent ──Streamable HTTP + API key──┐
Developer CLI / CI ──REST + API key──────────────┤
▼
Lambda Function URLs ──► DynamoDB (single table)Why MCP-first?
Translation management is mostly conversation + judgement: "add a French locale", "translate
the untranslated checkout strings", "what does cart.empty say in German?". An agent with the
right tools does this naturally. The connected LLM does the translating itself — there's
no separate machine-translation engine to pay for or configure.
The CLI exists for the things you should not hand to an LLM: deterministically exporting a JSON/YAML file, downloading translations, and syncing them in CI.
Related MCP server: i18n Agent
Features (v1)
MCP server with 36 tools: projects, locales, keys (with descriptions/context), translations, bulk fill, review workflow, and full user/member/API-key administration (incl. key revocation).
First-class RBAC. Global roles (
OWNER/ADMIN/MEMBER) + per-project roles (MANAGER/EDITOR/DEVELOPER/VIEWER). High-privilege users manage everyone else's access.Glossary + translation memory, and webhooks (HMAC-signed, via DynamoDB Streams) for change events.
API-key auth — simple bearer tokens, stored hashed. (OAuth/Cognito is a future option.)
Developer CLI —
login,init,pull,push,buildwith multi-target config and adapters for JSON (nested/flat), YAML, Flutter ARB, Java.properties, CSV, Androidstrings.xml, and iOS.strings/.stringsdict(ICU-canonical plurals converted to each format's native form).DynamoDB single-table design, on-demand billing. Multi-tenant-ready (
orgIdon every record).
Repository layout
Package | What it is |
| Domain model, DynamoDB repository, RBAC, services, format adapters (the shared brain) |
| Stateless Streamable HTTP MCP server → Lambda |
| REST API for the CLI/CI → Lambda, plus the webhook dispatcher |
| The |
Try it locally
The fastest way to see Turjuman work — everything runs against a local
LocalStack (needs Docker + Node 24+), no cloud account needed.
Turjuman uses pnpm (pinned via package.json's packageManager field); run
corepack enable once to activate it.
pnpm install && pnpm run build
pnpm run localstack:up # start the shared LocalStack on :4566
cp .env.example .env # point the toolchain at LocalStack
# deploy into LocalStack with hot reload; prints the MCP/REST URLs + a fresh API key
pnpm run devpnpm run dev runs the real Lambda runtime in LocalStack (so DynamoDB Streams → webhooks fire too) and
hot-reloads your edits. Point your MCP client at the printed MCP URL with the printed API key and start
talking to it.
Self-host on AWS
Status: the CDK stack is conventional but has not yet been verified end-to-end against a live AWS account (see ROADMAP). Use the local path above to evaluate; treat the cloud deploy as beta and please report issues.
1. Deploy to your AWS account
Instantiate the TurjumanStack in a tiny CDK app and deploy it with the AWS CDK CLI. The construct
vendors its Lambda bundles, so there's no SAM CLI and no repo clone (see
Self-hosting for the full walkthrough and config):
npm install @turjuman/aws-cdk aws-cdk-lib constructs
cdk bootstrap # once per account+region (standard CDK bootstrap)
cdk deploy # prints McpUrl / ApiUrl / TableName as stack outputs@turjuman/aws-cdk is standalone-installable, so the day-to-day turjuman developer CLI stays a
lean, AWS-free install.
2. Your first owner + API key
Once the stack is up, create the first owner over HTTP and capture its key — printed once, and
saved to ~/.turjuman/auth.json so you're logged in:
turjuman bootstrap --url <ApiUrl> --email you@example.com --name "Your Name"It refuses to create a second owner once the deployment has users (returns 409), so re-running it
is safe.
3. Connect Claude Code (MCP)
Add to your .mcp.json (see .mcp.json.example):
{
"mcpServers": {
"turjuman": {
"type": "http",
"url": "<McpUrl>",
"headers": { "Authorization": "Bearer <your-api-key>" }
}
}
}Keep your key out of version control.
.mcp.jsonis often committed — prefer referencing the token via an environment variable / secret manager rather than pasting the literal key. If a key ever leaks, revoke it immediately with therevoke_api_keytool.
Then just ask: "Create a project called Web App with base locale en, add fr and es, and translate everything into French."
4. Sync files in your repo (CLI)
pnpm dlx turjuman login --url <ApiUrl> --key <your-api-key>
pnpm dlx turjuman init --project <proj_id> --format json-nested --path "locales/{locale}.json"
pnpm dlx turjuman pull # write locale files from Turjuman
pnpm dlx turjuman push # upload source keys / translationsDocumentation
The full documentation lives in docs/ and is published as a documentation site with
Mintlify — one source that serves human readers, external agents (Mintlify
auto-generates llms.txt / llms-full.txt and an "open in Claude/ChatGPT" menu per page), and the
agents working in this repo. Start here:
Get started: Introduction · Quickstart (deploy to AWS) · Try it locally (no AWS)
Concepts: Why MCP-first · Architecture · Lifecycle · Roles & permissions · How agents use Turjuman
Guides: Translate with MCP · Code mode · Sync with the CLI · Quality checks · Webhooks · Connect Claude Code
Reference: MCP tools · CLI commands · REST API · File formats · QA checks · Glossary
Self-hosting: Overview · Deploy to AWS · Configuration · Security & API keys
Development
pnpm install
pnpm run build
pnpm test # unit tests (hermetic)
# integration tests against an emulated AWS (LocalStack DynamoDB):
pnpm run localstack:up && pnpm run test:integration && pnpm run localstack:down
# full deployed end-to-end (SAM stack on LocalStack: Lambda Function URLs +
# the real DynamoDB Streams -> webhook flow). Just needs Docker:
pnpm run test:e2eFormatting & linting
Formatting and linting are handled by Biome (a single, fast
Rust-based replacement for Prettier + ESLint), configured in biome.json:
pnpm run check # format + lint, report only
pnpm run check:write # apply formatting + safe lint fixes
pnpm run format # format only
pnpm run lint # lint onlyYou rarely run these by hand. A pre-commit hook auto-formats staged files, CI
runs biome ci ., and — since this repo is developed primarily with Claude Code —
a PostToolUse hook (.claude/hooks/biome-format.sh) auto-formats each file as
the agent edits it. The generated docs/api-reference/openapi.json snapshot is
owned by gen:openapi and excluded from Biome.
See Contributing for the full testing guide (unit, LocalStack integration, and deployed end-to-end), which also runs in CI.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mogharsallah/turjuman'
If you have feedback or need assistance with the MCP directory API, please join our Discord server