# translated/lara-mcp [Health: Active]

**Category:** 🌎 Translation Services  
**Repository:** https://github.com/translated/lara-mcp  
**GitHub Stars:** 100  
**npm Downloads (last month):** 2664  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/translated-lara-mcp

## Description
MCP Server for Lara Translate API, enabling powerful translation capabilities with support for language detection and context-aware translations.

## Tools
Capabilities this server exposes over MCP:

- **translate** — Translate text between languages with support for context, instructions, translation memories, glossaries, and multiple styles (faithful/fluid/creative)
- **detect_language** — Detect the language of a given text or array of texts
- **list_languages** — List all supported language codes
- **list_memories** — List all translation memories in your account
- **create_memory** — Create a new translation memory
- **update_memory** — Update a translation memory's name
- **delete_memory** — Delete a translation memory
- **add_translation** — Add a translation unit (source + target pair) to a memory
- **delete_translation** — Delete a translation unit from a memory
- **import_tmx** — Import a TMX file into a memory
- **check_import_status** — Check the status of a TMX import job
- **list_glossaries** — List all glossaries in your account
- **get_glossary** — Get details of a specific glossary
- **create_glossary** — Create a new glossary
- **update_glossary** — Update a glossary's name
- **delete_glossary** — Delete a glossary
- **add_glossary_entry** — Add or replace a term entry in a glossary
- **delete_glossary_entry** — Delete a term entry from a glossary
- **import_glossary_csv** — Import entries from a CSV file into a glossary
- **check_glossary_import_status** — Check the status of a glossary CSV import job
- **export_glossary** — Export a glossary as CSV
- **get_glossary_counts** — Get the number of entries in a glossary

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "lara-mcp": {
    "command": "npx",
    "args": ["-y","@translated/lara-mcp@latest"],
    "env": {
      "LARA_ACCESS_KEY_ID": "",
      "LARA_ACCESS_KEY_SECRET": ""
    }
  }
}
```

**Requires environment variables:** `LARA_ACCESS_KEY_ID`, `LARA_ACCESS_KEY_SECRET` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What translated/lara-mcp MCP server does

translated/lara-mcp exposes Lara Translate through the Model Context Protocol. It supports direct text translation, language detection for one or more text values, and lookup of supported language codes. Translation requests can include contextual information, instructions, translation memories, glossaries, and one of three styles: faithful, fluid, or creative.

The server also provides account-level operations for translation memories and glossaries. Memories can be created, renamed, removed, populated with source-and-target translation units, or loaded from TMX files. Glossaries can be created, renamed, deleted, inspected, populated with term entries, imported from CSV, exported as CSV, and checked for entry counts.

## How it works

The hosted service is available at `https://mcp.laratranslate.com/v1`. Clients connect to that URL and authenticate through OAuth 2.0 in a browser using Lara Translate credentials. Existing connectors using `https://mcp-v2.laratranslate.com/v1` continue to work.

Access-key authentication is also supported. In that mode, the client configuration supplies a Lara access key ID and secret rather than relying on browser login. Self-hosted deployments communicate with the MCP client over stdio and call the Lara Translate API with those credentials.

Usage metrics are enabled by default. Reported events include authentication results and per-tool success or error events. Metrics include account and request metadata such as tool name, timing, character counts, selected language tags, client information, transport, operating system, and Node.js version. Translated text, translations, credentials, glossary and memory IDs, instructions, context, and raw client identifiers are excluded from the listed metrics.

## Setup and configuration

For a hosted connection, add `https://mcp.laratranslate.com/v1` to the MCP client. Claude Desktop uses its custom connector settings; Cursor accepts the URL in `~/.cursor/mcp.json`; Claude Code can add it with an HTTP transport command. VS Code with GitHub Copilot, Windsurf, Cline, Continue, and other clients use their respective MCP configuration and OAuth flow.

A local Node.js deployment uses the `@translated/lara-mcp@latest` package through `npx` and requires Node.js 22.23.4 or later. Docker is another stdio option, using the `translatednet/lara-mcp:latest` image. Building from source requires Node.js 22.23.4 or later and pnpm; the project can also be built into a Docker image.

Self-hosted configurations must provide `LARA_ACCESS_KEY_ID` and `LARA_ACCESS_KEY_SECRET`. The hosted endpoint does not require API keys in the client configuration when OAuth is used.

## Tools and capabilities

- Translate text with context, instructions, memories, glossaries, and selectable styles.
- Detect the language of a single text or an array of texts.
- List supported language codes.
- Create, rename, delete, populate, and import translation memories; monitor TMX imports.
- Create, inspect, rename, delete, populate, import, export, and count glossary entries; monitor CSV imports.

## Limitations and notes

The hosted endpoint requires an MCP client that supports the configured HTTP connection and its OAuth flow. Local operation requires Node.js or Docker, depending on the deployment method, plus Lara access credentials. Translation-memory and glossary operations act on resources in the authenticated Lara Translate account. Import operations are asynchronous and expose separate status-checking tools.

_Full upstream README: https://allmcps.com/mcp/translated-lara-mcp/readme_