Smartling MCP for AI. Manage global translation projects from chat.

Q: How do I find all my projects using Smartling (Translation Workflow API)?

Run listprojects. This tool quickly retrieves a list of every translation project you've set up in your account, giving you the IDs needed to work on them.

Q: Can I upload files and context separately with Smartling (Translation Workflow API)?

Yes. You use uploadfile for structured source code like JSON or XML bundles, and then use uploadcontext specifically for visual aids like screenshots.

Q: What is the difference between creating a job and adding content? (Smartling (Translation Workflow API))

Use createjob to initialize the container—it makes the workspace available. Then, use addcontenttojob to put specific resources or strings into that already running job.

Q: After translations are done, how do I get them? (Smartling (Translation Workflow API))

You call downloadtranslatedfile. This tool pulls the final output file for a specific language and project directly into your agent's output.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

How this MCP server connects to your AI agent

Smartling (Translation Workflow API) automates complex localization tasks. Connect this server to manage projects, upload source files (JSON, XML), and create translation jobs—all through natural language commands.

It lets you track job progress, add visual context for translators, and download completed translations without leaving your chat interface.

What AI agents can do with Smartling (Translation Workflow API) Automation

Add content to job

Adds specific content segments to an existing translation job in a project.

Create job

Sets up and initializes a brand new translation job within a specified project.

Download translated file

Retrieves the final translated file output for a given locale and content set.

+ 4 more capabilities included

List and Inspect Projects

View all Smartling projects and retrieve detailed information about a specific project using list_projects or get_project.

Upload Source Content

Send raw content files (JSON, XML, etc.) to the system for translation processing via upload_file.

Provide Visual Context

Attach screenshots or HTML context using upload_context, helping translators write accurate localized strings.

Initiate Translation Jobs

Create a new translation job within an existing project using the create_job tool.

Add Content to Job

Incrementally add more specific content segments to a running job using add_content_to_job.

Download Completed Translations

Retrieve the final, translated output file for a given locale with download_translated_file.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

What AI agents can do with Smartling (Translation Workflow API) MCP Server: 7 Tools for Localization

Manage the entire localization lifecycle by listing projects, uploading content, creating jobs, and downloading translated files through natural language commands.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Smartling (Translation Workflow API) on Vinkius

Add Content To Job

Adds specific content segments to an existing translation job in a project.

Create Job

Sets up and initializes a brand new translation job within a specified project.

Download Translated File

Retrieves the final translated file output for a given locale and content set.

Get Project

Fetches detailed status information for one specific Smartling project ID.

List Projects

Returns a list of all available translation projects managed in your Smartling...

Upload Context

Attaches visual assets or UI context (like screenshots) to assist translators with localization accuracy.

Upload File

Sends source content files, such as JSON or XML resource bundles, into the translation system.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Smartling integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "smartling-translation-workflow-api": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Smartling tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"smartling-translation-workflow-api": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Smartling (Translation Workflow API), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Smartling. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Managing global translations usually means switching between three different apps., Solved with Vinkius AI Gateway

Today, launching a translation isn't one click. You jump into your project dashboard to find the ID. Then you download source files and upload them to version control. After that, you open a separate localization tool to track job progress, manually copying IDs and status updates between three different tabs just to get started.

With this MCP server, those steps collapse into a chat window. You tell your agent to run `list_projects`, and it spits out the ID. Then you use `upload_file` in the same thread, all while keeping track of job progress with simple calls like `get_project`. It keeps everything connected.

Smartling (Translation Workflow API): Control your content lifecycle.

The biggest time sink is the handoff. You finish writing source files, but then you have to manually upload them, ensure they are grouped into a job, and remember which specific locale needs attention. If you miss one step, the entire build breaks because the content isn't properly containerized.

This server handles that sequencing for you. By using `create_job` followed by targeted calls like `add_content_to_job`, your agent manages the project lifecycle from start to finish. You just tell it what needs translating, and it handles the structure.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

localization

translation-api

i18n

l10n

workflow-automation

What your AI can actually do with this

Look, you're managing localization jobs in Smartling; you don't wanna be clicking through a bunch of different dashboards just to get strings translated. You need your AI client—your agent—to handle the whole workflow right here. This server lets you talk to Smartling using natural language commands and manage every part of the content process.

Viewing and Inspecting Projects:
You can start by getting an overview of everything you're working on. Use list_projects to see all the translation initiatives managed in your Smartling account. If you need the deep details on just one job, use get_project with a specific project ID; it pulls back all the status info you need.

Preparing Source Content:
Before a translator can do squat, they gotta have content. You send raw source files—think JSON, XML, or whatever resource bundle format you're using—with upload_file. It dumps that stuff right into the system for processing. But wait, it gets better. Translators need context to get it right; they can't just guess what a button says.

You attach visual assets, like screenshots or HTML snippets, using upload_context. This helps your linguists write accurate localized strings because they see exactly how the text appears in the app.

Managing Jobs:
When you're ready to kick off the translation work, you use create_job to set up and initialize a brand new job inside an existing project. Once that job is live, and maybe you realize you missed some strings or need to add more specific content chunks—like legal disclaimers or product names—you don't restart everything.

You just call add_content_to_job, which increments the running job with those extra segments. That keeps your whole process super tight for the linguists.

Getting the Final Output:
The last thing you wanna do is manually download files from a website. When the translations are done, you use download_translated_file. You specify the locale and the content set, and boom—it retrieves the final translated file output right into your environment. It's that simple.

Basically, it handles everything: finding what projects exist (list_projects), digging deep on a specific project (get_project), feeding the raw files (upload_file), giving translators pictures to look at (upload_context), kicking off the work cycle (create_job), adding more strings mid-stream (add_content_to_job), and finally, grabbing the finished goods (download_translated_file). It keeps your whole localization pipeline running without you ever leaving your chat interface.

Built · Hosted · Managed by Vinkius Smartling Translation API - Manage Localization Jobs

Server ID 019e5d56-4c99-71e3-9aa8-3722dc8ae6ca

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is you use your AI client to sequence calls across these tools: Discovery -> Preparation -> Execution -> Output.

First, run list_projects to find the ID of the project you need to work on. Then, use get_project to confirm its current status.

Next, upload all source data using upload_file and add visual guides with upload_context. After that, run create_job to start the translation process.

Finally, monitor progress by checking the job details. When finished, use download_translated_file to get the output.

Who is this actually for?

Anyone dealing with content for multiple markets needs this. Specifically, the localization manager who hates switching between dashboard tabs and the developer who just wants to automate file transfers from their IDE. It's for people whose job involves keeping global content current.

Localization Manager

They use list_projects to keep track of every market rollout and manage the lifecycle by creating jobs using create_job.

Developer

They rely on uploading resource files with upload_file directly from their code editor, then downloading the final translation output to merge into the app.

Content Strategist

They ensure quality by attaching visual references via upload_context, guaranteeing translators understand UI placement and tone.

What Changes When You Connect

Stop manually tracking job progress. Use get_project to pull the real-time status of a specific localization initiative into your conversation, instead of logging into a separate dashboard.

Never lose source files again. When you run upload_file, the system accepts JSON, XML, and HTML formats, handling resource bundles directly from your agent.

Improve translator accuracy immediately. Running upload_context lets you attach screenshots or UI examples alongside your strings, so they know exactly where the text lives in the app.

Build structured workflows: You can sequence commands—run list_projects, then create_job, and finally add_content_to_job—all without leaving your IDE or chat window.

Get translations fast. Once work is done, simply call download_translated_file. The output file arrives ready for integration into your build pipeline.

See it in action

01 01

Need to localize a new mobile feature?

A developer needs to translate 'settings.json' for the next release. They start by running list_projects to find the 'Mobile App Localization' ID. Then, they use upload_file with the new JSON, followed by create_job. This sets up a clean workflow and gets the process started.

02 02

A UI element needs better context for translators.

The content team finds that key phrases are being mistranslated because linguists don't know how they look in the app. They use upload_context to attach a screenshot of the 'Login Screen'. This visual guide makes sure all future translations are accurate and consistent.

03 03

I need to update content for an ongoing campaign.

The marketing team needs to inject new promotional text into a live project. Instead of starting from scratch, they use get_project to check the current job status, and then call add_content_to_job to append the fresh copy without disrupting the rest of the work.

04 04

The build is ready, time to download translations.

After monitoring a job's progress via get_project, and confirming it's marked 'Complete', the agent runs download_translated_file for the German locale. The resulting file is immediately available for the CI/CD pipeline.

The honest tradeoffs

Trying to upload everything at once

Anti-pattern

A user might try to dump a massive zip file containing sources, context images, and project IDs into one prompt. The system gets confused about what's source code vs. visual instruction.

The Fix

Keep the steps separate: First, use upload_file for all code bundles. Second, run upload_context for screenshots or UI guides. Then, create the job using create_job. Don't combine them.

Skipping project discovery

Anti-pattern

A user just assumes they know the correct Project ID and tries to run add_content_to_job without verifying it. They end up modifying content in the wrong market or old version.

The Fix

Always start by running list_projects. This ensures you have the correct, current project ID before attempting any write operations.

Forgetting to download the final file

Anti-pattern

The agent successfully completes a job and tells the user it's done. The conversation ends there, leaving the user with no actual translation data to give to the devs.

The Fix

After confirming completion via get_project, always follow up with download_translated_file immediately. That’s how you get the usable asset.

When It Fits, When It Doesn't

Use this server if your job involves managing content for multiple languages or markets, and you need to automate file handoffs (JSON/XML) between your code repository and a translation service. It excels at guiding data through a structured process: Source -> Context -> Job -> Output.

Don't use it if all you need is simple text translation without managing the source files. For that, a basic chat-based translator tool works fine. But if you have to manage projects and content types—i.e., if you need to run upload_file or check job status with get_project—this server is necessary.

Questions you might have

How do I find all my projects using Smartling (Translation Workflow API)? +

Run list_projects. This tool quickly retrieves a list of every translation project you've set up in your account, giving you the IDs needed to work on them.

Can I upload files and context separately with Smartling (Translation Workflow API)? +

Yes. You use upload_file for structured source code like JSON or XML bundles, and then use upload_context specifically for visual aids like screenshots.

What is the difference between creating a job and adding content? (Smartling (Translation Workflow API)) +

Use create_job to initialize the container—it makes the workspace available. Then, use add_content_to_job to put specific resources or strings into that already running job.

After translations are done, how do I get them? (Smartling (Translation Workflow API)) +

You call download_translated_file. This tool pulls the final output file for a specific language and project directly into your agent's output.

How do I authenticate and connect my AI agent to Smartling using this server? +

You must provide your Smartling User Identifier and User Secret credentials when setting up the connection. The agent uses these keys to authorize all subsequent calls, ensuring only your account can manage jobs.

If I use `add_content_to_job` but include an incorrect Job ID, what happens? +

The server will immediately reject the request and return a specific error code. This tells you that the job doesn't exist or that your agent lacks permission to modify it.

How can I use `get_project` to check which locales are available for translation? +

The tool returns comprehensive metadata for a specific Smartling project. Look for the 'locales' array in the response payload; this lists every language code currently attached to that project.

When I call `upload_file`, how do I ensure content is authorized right away? +

The file upload tool accepts an authorization flag in the payload. Including this parameter forces Smartling to automatically authorize the content upon successful upload, skipping manual review steps.

Can I upload a file and have it immediately ready for translation? +

Yes! When using the upload_file tool, set the authorize parameter to true. This will automatically authorize the content for translation in your project.

How do I group multiple files into a single translation task? +

First, use create_job to create a new translation job. Then, use add_content_to_job for each file URI you want to associate with that specific job UID.

Can I provide visual context to help translators? +

Absolutely. Use the upload_context tool to send visual references (like screenshots or HTML) to your project, ensuring higher translation quality.

How this MCP server connects to your AI agent

What AI agents can do with Smartling (Translation Workflow API) Automation

Add content to job

Create job

Download translated file

What AI agents can do with Smartling (Translation Workflow API) MCP Server: 7 Tools for Localization

Add Content To Job

Adds specific content segments to an existing translation job in a project.

Create Job

Sets up and initializes a brand new translation job within a specified project.

Download Translated File

Retrieves the final translated file output for a given locale and content set.

Get Project

Fetches detailed status information for one specific Smartling project ID.

List Projects

Returns a list of all available translation projects managed in your Smartling...

Upload Context

Attaches visual assets or UI context (like screenshots) to assist translators with localization accuracy.

Upload File

Sends source content files, such as JSON or XML resource bundles, into the translation system.

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more

Managing global translations usually means switching between three different apps., Solved with Vinkius AI Gateway

Smartling (Translation Workflow API): Control your content lifecycle.

localization

translation-api

i18n

l10n

workflow-automation

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

Need to localize a new mobile feature?

A UI element needs better context for translators.

I need to update content for an ongoing campaign.

The build is ready, time to download translations.

The honest tradeoffs

Trying to upload everything at once

Skipping project discovery

Forgetting to download the final file

When It Fits, When It Doesn't

Questions you might have