ModelsAtlas
Explore
Atlas / MCP servers / translated / Lara Translate

Lara TranslateCAUTION

mcp/translated/lara-translate
MCP server by translated · Audited 2026-10-07
⚑ Report / re-scanSource ↗
Verdict
CAUTION
Grade
B
Trust score
88 /100
Exposed tools
22 8r · 10w · 4d
Transport
streamable-http
License
MIT
Stars
99
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server for Lara Translate, enabling professional translation capabilities with support for language detection, context-aware translations, translation memories, and glossaries.

Lara leverages Translation Language Models (T-LMs) trained on billions of professionally translated segments, delivering domain-specific translations that capture cultural nuances and industry terminology that general-purpose LLMs often miss.

[](https://github.com/translated/lara-mcp/blob/main/LICENSE) [](https://hub.docker.com/r/translatednet/lara-mcp) [](https://www.npmjs.com/package/@translated/lara-mcp)

Quick Start

Pick your client below — no API keys needed, just log in through your browser.

Claude Desktop

  1. Go to Settings > Connectors
  2. Click Add Custom Connector
  3. Enter the name: Lara
  4. Enter the URL: https://mcp-v2.laratranslate.com/v1
  5. Click Add, then click Connect
  6. Log in with your Lara Translate credentials in the browser

Done — Lara Translate is now available in your conversations.

Cursor

Once Lara Translate is listed in the official Cursor plugin marketplace, install it from inside Cursor:

  1. Open the plugin browser and search for Lara Translate.
  2. Click Install.
  3. The first time you use a Lara tool, your browser will open to authenticate.

In the meantime, or for manual installation, see the Client Setup Guide.

Claude Code

Once Lara Translate is listed in the official Claude Code plugin marketplace, install it from inside Claude Code:

/plugin

Search for Lara Translate and install. The first time you use a Lara tool, your browser will open to authenti

Read from source at commit 5200cfd20561OBSERVED · 2026-10-07
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add lara-mcp -- npx -y @translated/[email protected]
claude-desktop
{
  "mcpServers": {
    "lara-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@translated/[email protected]"
      ]
    }
  }
}
03

Exposed tools (22)

8 read · 10 write · 4 destructive. Blast radius: 4 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
add_glossary_entrywriteAdds or replaces an entry in a glossary in your Lara Translate account. Supports both monodirectional and multidirectional glossaries.
add_translationwriteAdds a translation to a translation memory in your Lara Translate account.
check_glossary_import_statuswriteChecks the status of a glossary CSV import job started by import_glossary_csv. Poll this tool with the import_id returned from import_glossary_csv until the import is complete.
check_import_statuswriteChecks the status of a TMX import job started by import_tmx. Poll this tool with the import_id returned from import_tmx until the import is complete. The response includes a progress field to track completion.
create_glossarywriteCreate a glossary with a custom name in your Lara Translate account. Glossaries enforce specific terminology during translation.
create_memorywriteCreate a translation memory with a custom name in your Lara Translate account. Translation memories store pairs of source and target text segments (translation units) for reuse in future translations.
delete_glossarydestructiveDeletes a glossary from your Lara Translate account.
delete_glossary_entrydestructiveDeletes an entry from a glossary in your Lara Translate account. Use term for monodirectional glossaries or guid for multidirectional glossaries.
delete_memorydestructiveDeletes a translation memory from your Lara Translate account.
delete_translationdestructiveDeletes a translation from a translation memory in your Lara Translate account.
detect_languagereadDetects the language of the provided text. Returns the detected language, content type, and a list of predictions with confidence scores. Accepts a single string or an array of strings (up to 128 elements).
export_glossaryreadExports a glossary as CSV from your Lara Translate account. Supports unidirectional and multidirectional formats.
get_glossaryreadRetrieves a specific glossary by ID from your Lara Translate account. Returns null if the glossary is not found.
get_glossary_countsreadRetrieves the term and language counts for a glossary in your Lara Translate account.
import_glossary_csvwriteImports a CSV file into a glossary. Supports unidirectional and multidirectional formats. This is an async operation that returns an import job object containing an import_id. Poll with check_glossary_import_status using the returned import_id until the import is complete.
import_tmxwriteImports a TMX file into a translation memory. This is an async operation that returns an import job object containing an import_id. Poll with check_import_status using the returned import_id until the import is complete.
list_glossariesreadLists all glossaries in your Lara Translate account. Glossaries are collections of terms with their translations that enforce specific terminology during translation.
list_languagesreadLists all supported languages in your Lara Translate account.
list_memoriesreadLists all translation memories in your Lara Translate account.
translatereadTranslate text between languages using Lara Translate. Supports language detection, context-aware translations, translation memories, and glossaries.
update_glossarywriteUpdates the name of a glossary in your Lara Translate account.
update_memorywriteUpdates a translation memory in your Lara Translate account.
04

Trust audit

CAUTIONgrade B · trust 88/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (2 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (10)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
delete_glossary, delete_glossary_entry, delete_memory, delete_translation
Why it matters. 4 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
MEDIUMAuth / authz · mcp.remote_no_auth · CWE-287, CWE-862
streamable-http
Why it matters. a network transport with no auth environment variable found
Fix. require a token
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/__tests__/server/era.http.test.ts:11
import { PACKAGE_VERSION } from "../../version.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/__tests__/server/era.http.test.ts:33
const { RestServer } = await import("../../rest/server.js");
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/__tests__/server/era.http.test.ts:34
const { default: mcpRouter } = await import("../../rest/routes/mcp.js");
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/__tests__/server/era.http.test.ts:35
const { ListTools } = await import("../../mcp/tools.js");
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/__tests__/server/mcp.server.test.ts:2
import { PACKAGE_VERSION } from "../../version.js";
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
src/__tests__/server/era.http.test.ts:48
url = new URL(`http://127.0.0.1:${(httpServer.address() as AddressInfo).port}/v1`);
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/node, @modelcontextprotocol/server, @translated/lara, cors, express, helmet, hono, pino
Why it matters. 21 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
docs/client-setup.md:273
- If using Access Key: verify your credentials are correct and active in your [Lara Translate account](https://laratranslate.com)
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 5200cfd20561full audit observations/trust-audit/mcp-server/translated__lara-translate.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-075200cfd20561CAUTIONB88first audit
06

Questions

What tools does Lara Translate expose?

22 in total: 8 read-only, 10 that write, and 4 that can delete or overwrite (delete_glossary, delete_glossary_entry, delete_memory, delete_translation). Every one is listed on this page with its risk.

Is Lara Translate safe to connect to an agent?

With care. The audit graded it B (88/100) and found 10 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 4 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Lara Translate need?

No credential environment variables were found in its source, so it appears to need none.

How does Lara Translate run?

It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @translated/lara-mcp at 2.0.0.

How current is this page?

The grade is for one exact copy of the source (5200cfd20561), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement