Dualtran Mcp

io.github.seigwenPublished by GitHub account seigwenv0.1.0Updated Oct 24, 2026

Translate text with Google or your own AI model (BYOK, 20+ providers) from any MCP client.

VerifiedSTDIODesktop onlyProductivity & WorkflowAI & ML

Overview

AI-generated overview

Local MCP server that lets an assistant translate text using Google or your own AI provider key, from any MCP client.

What you can do
  • Translate a single piece of text, optionally choosing target language, source language and engine (Google or AI)
  • Translate up to 50 texts in one batched call
  • List available translation engines and whether AI configuration is present, without exposing the key
When to use it
Useful when you want an assistant to translate text or batches of strings inside your editor or chat client, either with free Google translation or with your own model provider account.
Requirements
Runs locally via npx (Node.js). Google translation works without a key or account. The optional AI engine needs a provider id, model and API key, set through environment variables such as DUALTRAN_PROVIDER, DUALTRAN_MODEL and DUALTRAN_API_KEY, or a config file in the home directory; environment variables take precedence. Network access to the chosen translation service.
Before you install
The AI engine requires your own provider API key, which is stored in an environment variable or a config file in your home directory; usage may be billed by that provider. Text you translate is sent to the selected translation service at the time of translation. The server itself reports no analytics or developer server.

Installation

In SourceWeft

  1. Open Dualtran Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

dualtran-mcp

An MCP (Model Context Protocol) server that translates text with Google or your own AI model (BYOK, 20+ providers) — usable from Claude Code, Claude Desktop, Cursor, Cline, VS Code and any other MCP client. Powered by @dualtran/core, the engine extracted from the DualTran browser extension.

Tools

ToolWhat it does
translate_textTranslate one piece of text. Optional target_lang, source_lang, engine (google | ai).
translate_batchTranslate up to 50 texts in one call (one batched Google request).
list_enginesReport available engines and the AI configuration state (never the key).

Install

bash
npx -y dualtran-mcp# or straight from this repository (works today, no registry needed):npx -y github:seigwen/dualtran-mcp

Configure

Google works out of the box — no key, no account.

For the AI engine (optional), configure a provider once — either with environment variables:

DUALTRAN_PROVIDER=openai        # openai | anthropic | google | deepseek | mistral | groq | xai | …DUALTRAN_API_KEY=sk-…DUALTRAN_MODEL=gpt-4o-miniDUALTRAN_BASE_URL=              # optional endpoint overrideDUALTRAN_TARGET_LANG=en         # default target languageDUALTRAN_ENGINE=google          # default engine: google | ai

or with ~/.dualtran/config.json:

json
{ "provider": "openai", "apiKey": "sk-…", "model": "gpt-4o-mini", "targetLang": "en", "engine": "ai" }

Environment variables win over the file.

Client configuration

Claude Code (.mcp.json in the project, or claude mcp add):

json
{  "mcpServers": {    "dualtran": {      "command": "npx",      "args": ["-y", "github:seigwen/dualtran-mcp"],      "env": { "DUALTRAN_TARGET_LANG": "en" }    }  }}

Cursor (~/.cursor/mcp.json) and Cline / other clients: same shape — command: npx, args: ["-y", "github:seigwen/dualtran-mcp"], optional env.

Privacy

No analytics, no accounts, no developer server. Text goes only to the translation service you chose, at the moment you translate. See PRIVACY.md.

Development

bash
node scripts/sync-core.mjs   # vendors @dualtran/core into vendor/ (committed)npm installnpm test                     # tsc build + vitest (in-memory server, real stdio e2e, stdout purity scan)

License

MIT — the bundled @dualtran/core portion is MPL-2.0.

Languages

The engine itself has no interface: strings this package exposes are MCP tool names/descriptions and parameter docs, which LLM clients and protocol tooling consume in English. Localising them would hurt discoverability, so they stay English by policy. Any future user-facing surface must follow the DualTran i18n standard (38 catalogues, locales/<code>/messages.json).

Source: README.md at commit 31bab75

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestOct 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.