Consensus translation through 22 AI models, with language lookup and MCP access over a hosted HTTP endpoint.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
Clients with native remote MCP support can connect directly to this URL instead of the install method above.
π‘ Remote servers are added in the app, not the config file: Customize β Connectors β Add custom connector, then paste this URL.
Inspect callable tools, capabilities, and parameters exposed to AI agents by MachineTranslation.com MCP.
MachineTranslation.com MCP MCP server exposes translation capabilities to MCP-compatible clients through the MachineTranslation.com service. Its main tool, smart_translate, accepts text and source and target languages, then produces a SMART translation based on consensus across 22 AI translation models. Rather than returning the result of one model, the service selects the output the models agree on.
The list_languages tool returns the supported language codes and their names. This can help an agent discover valid language values before calling smart_translate.
The service is intended for workflows such as translation assistance, localization review, multilingual marketing content, and application development that needs access to supported language pairs. The README identifies Claude, ChatGPT, Cursor, and other MCP clients as usage contexts; this listing specifically provides a hosted MCP connection rather than a local package to install.
The MachineTranslation.com MCP MCP server uses streamable HTTP at https://www.machinetranslation.com/mcp. The endpoint must be entered without a trailing slash. MCP clients connect to the endpoint, complete authentication, and then expose the two tools to an assistant.
Authentication uses OAuth 2.1 for connectors. During connector setup, the client can dynamically register, so the OAuth client ID and secret are left empty. Developer clients may also support an optional personal access token, according to the README.
Each successful SMART translation consumes credits from the connected MachineTranslation.com account. The service does not use submitted translation content to train AI models, according to the projectβs privacy documentation.
To use the MachineTranslation.com MCP MCP server, create a MachineTranslation.com account with a verified email and an active paid plan that includes credits. Supported plan types include Pro, limited-time access plans, and active legacy starter or advanced subscriptions. Free accounts cannot connect.
In Claude or ChatGPT connector settings, add a custom MCP server and enter this exact URL:
https://www.machinetranslation.com/mcp
Leave OAuth Client ID and Secret empty, choose Connect, sign in using an available account method, and authorize access. Cursor and other developer clients can use the same hosted endpoint with the authentication method they support. No local installation or API key is required for the connector flow.
smart_translate: Requests a SMART translation using source text, source language, and target language. The result is based on multi-model agreement.list_languages: Lists supported language codes and language names.The MachineTranslation.com MCP MCP server requires an eligible paid account; having an account alone is not enough. Each smart_translate request requires at least 30 credits, or one credit per source word when that amount is higher. The account has a default limit of 50 SMART calls per UTC day, and the maximum source length is controlled by the siteβs WORD_LIMIT setting.
Credits are deducted after each successful SMART translation, so agents should avoid repeated calls when a single result is sufficient. The available language codes and maximum source size determine whether a particular translation request can run. The endpoint is hosted remotely, and the supplied material does not describe a local server command or package installation.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/machinetranslation-com-mcp)<a href="https://allmcps.com/mcp/machinetranslation-com-mcp"><img src="https://allmcps.com/api/badge/machinetranslation-com-mcp?style=directory" alt="MachineTranslation.com MCP on AllMCPs" /></a>