Think of the Transifex MCP Server as a translator's helper for your AI tools. It acts as a bridge that connects your favorite AI apps—like Cursor, Claude Code, Codex, or Windsurf—directly to your Transifex account.

Instead of opening a browser, clicking through menus, and copying text back and forth, you can simply talk to your AI app in plain English. For example, you can tell it to "Show me which projects need translating" or "Create a new AI translation task," and the AI will take care of it automatically.

What Can Your AI Agent Do?

Once connected, your AI agent can interact with Transifex to handle these tasks:

Find Your Work: See all the organizations and projects you have access to.
Check Status: Look at project details, find out which languages are being targeted, and see how close a translation is to being finished.
Prioritize Tasks: Compare different projects in your organization to see which ones have the most untranslated words, so you know what to work on first.
Manage Tasks: Look at, create, or change translation tasks (including setting up automated AI translations).
Assign Self to a Task: Have the AI automatically assign or unassign your account to specific human-translation tasks.

Setup Requirements

Before you begin, make sure you have:

A Transifex account with access to an organization.
A Transifex API token. You can generate one by logging into Transifex and following their API authentication guide.
An AI tool (MCP Host) that supports external connections (like Cursor or Codex).

Your Connection Header

The AI tool will use your API token to log in. It sends it behind the scenes using a standard format that looks like this:

Plaintext

Authorization: Bearer <Your-Transifex-API-Token>

Connection Web Addresses (URLs)

To set up the MCP server you will need the following URL:

[https://mcp.transifex.ai/mcp]

Configuration Examples

Here is how to plug the server into popular AI development environments. Replace <Transifex API token> with your actual secret token.

1. Codex Configuration

Open or create a file named config.toml inside your project's .codex folder, and add the following lines:

Ini, TOML

[mcp_servers.transifex] transport = "streamable_http" url = "https://mcp.transifex.ai/mcp" enabled = true [mcp_servers.transifex.http_headers] Authorization = "Bearer <Your-Transifex-API-Token>"

(Note: If you are using the testing/staging environment, change the URL to the staging address and use your staging token.)

2. Cursor Configuration

Open or create a file named mcp.json inside your project's .cursor folder, and add this code:

JSON

{   "mcpServers": {     
             "Transifex": { 
                     "url": "https://mcp.transifex.ai/mcp",
                      "headers": {"Authorization": "Bearer <Your-Transifex-API-Token>"       }     
        }   
     } 
}

Testing the Connection

To make sure everything is working perfectly, open your Cursor AI sidebar chat and type:

"List the Transifex organizations I can access"

If everything is set up correctly, the AI will talk to Transifex and reply with a list of the organizations you belong to.

Speed Limits (Rate Limiting)

To keep the system running smoothly for everyone, the server limits how fast requests can be made using your token.

Normal speed: Up to 25 requests per second.
Short bursts: Up to 50 requests at once for brief moments.

Reference Library: What Tools Does the AI Have?

When you ask your AI assistant to do something, it chooses from a specific list of built-in "tools." Here is a plain-language breakdown of what the AI can call on your behalf:

Organizations & Projects

get_organizations: Asks for a list of all your Transifex organizations. The AI uses this if it doesn't know where to look yet.
get_organization_overview: Looks at an entire organization to compare projects and sort them by how many words are left to translate. This is great for spotting what needs urgent attention.
get_projects: Shows a quick summary list of projects (names, default languages, and descriptions).
get_project: Pulls up the complete settings for a specific project, including behind-the-scenes settings like Translation Memory or AI automation.
get_project_overview: Pulls a massive summary of a single project, showing target languages, recent file updates, and translation percentages all at once.

Files, Languages, & Progress

get_resources: Lists the files (resources) that exist into a specific project.
get_resource: Grabs deep details about a single file, like how many total words and sentences it has.
get_languages: Shows all the languages this project is being translated into.
get_strings: Looks up hidden reference ID tracking codes (hashes) for the text blocks. Note: This looks at system IDs, not the actual text content.
get_project_language_stats & get_resource_language_stats: These tools show progress counts (how many words are translated, reviewed, proofread, or untranlsated) for an entire project or just a single file.

Managing Work & Assignments

get_tasks & get_task: Lists all or inspects one translation task (including automated AI jobs), showing due dates, priorities, and who is currently assigned to them.
get_task_subtasks: Breaks down a task to show the individual steps required for different languages.
create_task: Builds a brand new translation task. It can set up human translation, human review, or fully automated AI translation options.
edit_task: Updates a task's name, description, priority rank, or due date.
set_my_task_assignment: Adds or removes you from a specific task step.

⚠️ Important Security Rule: The server derives who you are strictly from your secure API token. The AI can assign or unassign your account to steps, but it cannot use these tools to assign work to other random users.

Transifex MCP Server Connection Guide