Transglot MCP

Connect transglot to claude.ai or Claude Code with your transglot login, or add the MCP server to Cursor, VS Code or any MCP client with a deploy token, then ask your agent to translate, review and sync your strings.

Your coding agent can work on your translations directly. The transglot MCP server (@transglot/mcp, built on the Model Context Protocol) gives an agent tools for your projects, so you can ask in plain language: "translate what is missing in French", "what does checkout.title say in German", "add our product name to the glossary as do-not-translate".

There are two ways to connect:

• With your transglot login, from claude.ai, Claude Desktop or Claude Code. transglot hosts the server, and one connection reaches every project you can work in, in the workspaces you choose. See Connect from claude.ai or Claude Code.
• With a deploy token, from any MCP client. The server runs on your machine and serves one project. See Run the server with a deploy token.

Connect from claude.ai or Claude Code

The hosted server's address is:

https://api.transglot.ai/mcp

Add a custom connector and paste the address above. If your claude.ai account belongs to an organization, its Owner may need to add the connector first. When transglot is listed in the Connectors Directory, you can add it from there instead.

Allow the connection

Your client opens transglot in your browser. Sign in if you are not signed in already, then:

1. Under Where it can work, choose the workspaces the connection may reach. A workspace you cannot choose says why: its plan has no API access, it requires two-factor sign-in and your login does not have it, connected apps are turned off there, or your role there cannot connect.
2. Under What it can do, choose what the app may do. Each choice is an ability; the code in parentheses is the one the tools table uses:
   • Read strings, translations and the glossary (read), always included;
     • Edit translations (write);
     • Download translation files (pull);
     • Upload source strings, which can start translation (push);
     • Start AI translation and QA, add languages, change the glossary and webhooks (manage).
3. Select Allow. transglot emails you that the app is connected.

If the page says Not verified by Transglot, the app chose its own name and transglot has not checked who made it. Allow it only if you started the connection yourself.

Who can connect, and what it can do

• You can connect in a workspace where you are the account Owner, an Admin or a Developer. Other roles, custom roles included, cannot.
• In each project, the connection acts with your own role there, narrowed to the abilities you chose.
• A Developer can allow read, write, pull and push. Only the account Owner and Admins can allow manage, so only their connections can add languages, start, retry and stop translation runs, run quality checks, and edit the glossary.
• In a project where your access is limited to some languages, the connection can only read and pull there.
• If a workspace requires two-factor sign-in, your login must have it, or that workspace's projects refuse the connection.
• Projects in a workspace whose plan has no API access refuse the connection. API access comes with Starter and above. See pricing.

Your agent gets the same 17 tools as the npm package, listed under Tools, plus list_projects in the hosted connector. list_projects lists the projects the connection can reach, with each one's id, languages and abilities. Every other tool takes an optional project argument, set to one of those ids. When the connection reaches exactly one project, project can be left out.

Disconnect

Open Settings, choose the You tab, then Connected apps. Each app shows the workspaces it reaches and what it can do. Disconnect stops it at once. To change its workspaces or abilities, disconnect it and connect again.

Leaving a workspace, or being removed from it, takes that workspace out of all your connections. If you join it again, connect again to reach it.

A connection keeps itself signed in while you use it. One left unused for 90 days expires, and you connect again.

Turn it off for a workspace or a project

• A whole workspace. The account Owner opens Settings, chooses the Workspace tab, then Security, and turns off Allow connected apps in this workspace. Connected apps stop reaching every project in the workspace at once. No connection is deleted, and turning it back on restores access.
• One person on one project. Once a connection has worked in a project, it appears on that project's API keys page (in the project, open Settings, choose the Project tab, then API keys), under API tokens, marked Connected app with the person it acts for. When an Admin revokes it, that person is cut off the project: none of the apps they connected can act there, and they get an email. Their connections keep working in other projects. The person is listed under Cut off from this project until an Admin selects Allow again.

Run the server with a deploy token

It stays in this page: nothing is sent anywhere. No token yet? Create one in your project under Settings → Developer → API tokens.

2. Add transglot to your agent

Claude Code: run this in your project

claude mcp add transglot --env TRANSGLOT_TOKEN=tgl_xxx -- npx -y @transglot/mcp

Then ask your agent: “Translate what is missing in French” or “What does checkout.title say in German?”

The server runs on your machine with npx, so you need Node.js 20 or later. One server serves one project: the deploy token decides which, and the token's abilities decide which tools work.

Get a deploy token

Open the project's API keys

In the console, open the project, then Settings, choose the Project tab, then API keys. Under API tokens, select New token.

Pick the abilities

For an agent that reads and edits translations, choose read, write and pull. Add manage if it should also start translation runs, run quality checks and edit the glossary. Choose the token's abilities has the full list.

Copy the token

The token is shown once. Paste it into the box above, or into your client's configuration below. More on tokens in Deploy tokens.

Tokens need a plan with API access, Starter and above. See pricing.

Point your agent at these docs

Agents read documentation better as plain text. Give yours llms.txt (an index of every page) or llms-full.txt (every page in one file), or the markdown of a single page: each page has a Copy Markdown button.

Set up any client by hand

The npm server speaks MCP over stdio. Every client runs the same command, npx -y @transglot/mcp, with the token in the TRANSGLOT_TOKEN environment variable. Replace tgl_xxx with your token. If the console showed the token with a number and a | in front, leave that part out: the shell reads | as a pipe.

claude mcp add transglot --env TRANSGLOT_TOKEN=tgl_xxx -- npx -y @transglot/mcp

The Integrations settings page in the app also has the Claude Code, Claude Desktop and Cursor snippets, under MCP server.

A configuration file that holds a token is a secret. Keep it out of version control, or use your client's way of reading the token from the environment.

Environment variables

Variable	Required	Description
TRANSGLOT_TOKEN	Yes	The deploy token. It is sent only in the Authorization header and is removed from any error text.
TRANSGLOT_BASE_URL	No	The API address. Default: https://api.transglot.ai. TRANSGLOT_URL, the CLI's variable, is used when this one is not set.

Without a token the server exits at once with transglot-mcp: TRANSGLOT_TOKEN is required. on stderr, which your client shows in its MCP log.

Tools

Read tools have no side effects. Tools that start a translation run or a quality check use the workspace's word allowance; their descriptions say so, so the agent and your client's approval prompt can tell.

Tool	What it does	Ability
get_project	Reads the project: name, source locale, every locale and the key count.	any of push, pull, manage
list_languages	Lists the project's locales and the source locale.	any of push, pull, manage
add_language	Adds a target language and, unless translate_now is false, starts a translation run into it. Workspace admins are notified. The token's creator must be allowed to add languages.	manage
get_translation	Reads one key in one locale: value, state, staleness and quality verdict.	read
upsert_translation	Writes one value, or its plural forms, for an existing key as a human edit. Editing the source locale can queue a translation run.	write
translate_missing	Starts a translation run that fills missing values. Never overwrites edited or reviewed translations.	manage
get_batch_status	Reads one translation run, optionally with its failed items.	any of push, pull, manage
list_batches	Lists recent translation runs, or only the active ones.	any of push, pull, manage
retry_failed_batch	Queues the failed items of a finished run as a new run.	manage
cancel_batch	Stops a running translation run. Unspent words return to the allowance.	manage
run_qa	Runs the AI quality check over target translations. Needs a plan with Quality mode (Team and above).	manage
glossary_list_terms	Lists glossary terms, 100 per page.	read
glossary_add_term	Adds an active glossary term: do-not-translate, forbidden, or with required translations.	manage
glossary_update_term	Replaces a glossary term by id.	manage
glossary_delete_term	Deletes a glossary term.	manage
pull_file	Exports one locale as a file, optionally only translations at a minimum state.	pull
push_file	Imports a file into one locale. Can delete keys missing from a source file.	push

pull_file and push_file in version 0.1.0 of the package handle json_flat, json_nested, android_xml, ios_strings, ios_stringsdict, flutter_arb, laravel_php and laravel_json. For other formats, use the CLI.

The glossary tools need a plan that includes the glossary (Starter and above). See pricing.

Choose the token's abilities

You want the agent to	Give the token
Read translations and the glossary only	read and pull
Also edit single translations	read, write and pull
Also sync whole files	add push
Also add languages, start, retry and stop translation runs, run quality checks, and edit the glossary	add manage

A tool the token's abilities do not cover returns an error with the hint The token lacks the "manage" ability. Issue a token that has it., naming the ability that is missing.

What the API does not offer

There are no tools to list or search keys, create or delete single keys, remove languages, or manage webhooks. Keys are created and removed by pushing source files, and languages are removed in the console.

Behaviour

• Transport: stdio for the npm package, with a deploy token; it writes diagnostics to stderr. Streamable HTTP for the hosted server at https://api.transglot.ai/mcp, with your transglot login over OAuth.
• Errors: API errors come back as tool errors in the form slug (HTTP status): detail, with a hint on what to do next.
• Rate limits: the API allows 60 requests per minute per token. The npm server retries a rate-limited request up to twice, waiting as the API asks, before it returns an error. A connection through the hosted server gets 60 requests per minute in each project, and retries once when the API asks it to wait 10 seconds or less.

Check the installed version with npx -y @transglot/mcp --version.

[

Overview

transglot translates your product with AI, checks every translation, and delivers it to your code, your content platforms and your apps.

](https://transglot.ai/docs/)[

Quickstart

Go from a new workspace to translated files in your repository in a few minutes.

](https://transglot.ai/docs/quickstart/)