Localization MCP#

The Lingo.dev MCP server gives AI coding assistants direct access to your localization engine configuration. Your assistant can create glossary entries, adjust brand voice, add instructions, configure models, and manage API keys — without leaving the conversation.

Why this matters#

When we studied how teams configure localization engines, we found that the majority of configuration changes happen during development — while reviewing translated UI, debugging a locale-specific issue, or onboarding a new market. Switching context to a dashboard breaks flow.

The Lingo.dev MCP server was purpose-built to keep localization engineering inside the development environment. Your AI assistant becomes a direct interface to your localization engine: it reads your current configuration, makes precise changes, and confirms the result — all within the same conversation where the problem surfaced.

Setup#

The MCP server requires an API key. Generate one in the API Keys section of the dashboard.

{
  "lingo": {
    "type": "http",
    "url": "https://mcp.lingo.dev/account",
    "headers": {
      "x-api-key": "your_api_key"
    }
  }
}

Capabilities#

Once connected, your AI assistant can manage your entire localization engine configuration through natural language.

Engine management#

Create, update, and inspect localization engines. Each engine is an independent configuration scope with its own models, glossary, brand voice, and instructions.

Brand voice#

Define how your product speaks in each locale. Set formal German ("Sie"), informal Italian ("tu"), or any per-locale tone. Your assistant can create, update, and remove brand voice profiles directly.

Glossary#

Add terms that must be translated exactly — or not translated at all. When you tell your assistant "make sure '911' translates to '112' in German," it creates the glossary entry immediately. Glossary entries are matched during localization via semantic similarity, so exact phrasing in source content doesn't need to match the glossary entry verbatim.

Instructions#

Encode linguistic rules that generic models miss. Space before percentage signs in French, adjective positioning in Spanish, pronoun formality per market. Your assistant adds these as locale-scoped instructions that apply to every translation.

LLM model configuration#

Configure which model handles each locale pair, with ranked fallbacks. Assign Claude for European languages, GPT for CJK, or any combination — your assistant manages the full model routing table.

Quality scoring#

Create and configure scorers that automatically evaluate translation quality. Define scoring criteria, select the evaluation model, and set sampling rates.

API keys#

Generate and revoke API keys for programmatic access to your localization engine.

Example workflows#

During code review: "The German translations sound too informal — switch the brand voice for de to use formal 'Sie' register."

Onboarding a new market: "Add Japanese as a target locale. Use Claude Sonnet for en→ja as primary, GPT-4.1 as fallback. Set the brand voice to polite-formal."

Fixing a translation bug: "Add a glossary entry: 'checkout' should stay as 'Checkout' in German — it's our product name, don't translate it."

Adding a linguistic rule: "In French, there should always be a non-breaking space before colons, semicolons, and question marks. Add that as an instruction for fr."

Next Steps#