MCP server for LingoHub — localization projects, resources, exports and repository pushes. For localization teams with a dedicated LingoHub API key. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"lingohub": {
"url": "https://lingohub.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"lingohub": {
"type": "http",
"url": "https://lingohub.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
Find your projects and inspect translation status by locale and resource file.
lingohub_list_projects lingohub_get_project_status
List the resource files in a project and download a selected text resource for review.
lingohub_list_resources lingohub_download_resource
Request a translation export, then check its status and download link.
Changes data · lingohub_request_export lingohub_get_export
List the existing files, then upload a resource file when requested. Import settings can overwrite or deactivate translation segments.
Changes data · lingohub_list_resources lingohub_upload_resource_file
The login page asks for your Lingohub API key.
Create it in Lingohub → workspace menu → Administration → API keys → Create a new API key (workspace owners and admins only), then copy it right away: it is shown only once. Give it only the permissions you want an AI to have (View only is enough for reading). Use a dedicated key for this UsefulAPI connection. Requested project text, resource files and context-image metadata pass to your chosen AI client and its LLM provider; connect only content you are authorized to share. When requested, tools create projects or exports, upload or delete resources/context images, and push changes to a configured repository. Revoke or disable this key in LingoHub to stop vendor access. Billing is per key; rotating it starts a new usage and billing identity.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Lingohub API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the LingoHub connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
lingohub_list_projects | read | List projects List every Lingohub project this API key can see (owned and shared, across workspaces). Each entry has the title, its links and the workspace_url + project_url slugs that every other tool needs. GET /v1/projects. |
lingohub_get_project | read | Get project One project: title, description, owner email, configured locales (project_locales), timestamps and links. GET /v1/{workspace_url}/projects/{project_url}. |
lingohub_get_project_status | read | Get project file status Translation status of one project: each resource file with per-locale segment counts (NOT_TRANSLATED, DRAFT, TRANSLATED, APPROVED, ...), failing quality checks, the export formats it supports and whether a Git repository is connected and can be pushed to. GET .../projects/{project_url}/status. |
lingohub_get_workspace_status | read | Get workspace translation status Translation progress of every project in one workspace: title, app URL, total segment count and per-locale counts by status (NOT_TRANSLATED, DRAFT, TRANSLATED, PREFILLED, APPROVED). GET /v1/{workspace_url}/projects/status. |
lingohub_create_project | write | Create project WRITE: create a new localization project in a workspace (needs settings-management permission on the key). Returns the new project with its links. It adds a project and changes nothing existing; repeating the call can create a second project. POST /v1/{workspace_url}/projects. |
lingohub_list_resources | read | List resource files List a project's resource files: name, locale and links (including a download link). GET .../projects/{project_url}/resources. |
lingohub_download_resource | read | Download resource file Download one resource file as text, in one language. file_name is the file name as list_resources shows it (the folder goes in `path`). Long files are cut at 40000 characters (truncated: true); use request_export for a full copy. GET .../projects/{project_url}/resources/{file_name}. |
lingohub_upload_resource_file | write | Upload resource file WRITE: upload one text resource file (JSON, properties, XLIFF, PO, ...) into a project. The language comes from the file name or from `language`. The import flags decide whether existing segments are changed or deactivated: with updating or deactivation on, translations already in Lingohub can be overwritten or switched off, so state the flags you want. Never retried. POST .../projects/{project_url}/resources. |
lingohub_delete_resource | write | Delete resource file WRITE, DESTRUCTIVE: delete a resource container: the source-language file AND all its target-language files with their translations. file_name and path must address the source-language file. This cannot be undone through the API. Never retried. DELETE .../projects/{project_url}/resources/{file_name}. |
lingohub_request_export | write | Request export Start an asynchronous export of a project's resource files as a ZIP. It creates an export job and changes no project data. Returns the export id; poll get_export until its status is SUCCESS to get the download URL. Without filters it exports every file and language. POST .../projects/{project_url}/exports. |
lingohub_get_export | read | Get export status Status of an export started with request_export: overall and per-file status (NEW, SCHEDULED, PROCESSING, SUCCESS, SKIPPED, ERROR), error details and, when done, the pre-signed download URL of the ZIP. GET .../projects/{project_url}/exports/{export_id}. |
lingohub_list_context_images | read | List context images List the context images (screenshots that show translators where a text is used) of a project, with connected-segment counts and processing status. Paginated; page is zero-based. GET .../projects/{project_url}/contextImages. |
lingohub_delete_context_image | write | Delete context image WRITE, DESTRUCTIVE: delete one context image and its connections to text segments. Never retried. DELETE .../projects/{project_url}/contextImages/{image_id}. |
lingohub_push_to_repository | write | Push translations to repository WRITE: push the project's resource files to its linked Git repository (GitHub, GitLab, Bitbucket or Azure DevOps; the connection must already exist). Depending on push_type this commits to a branch or opens a pull request, so it changes the user's repository. Never retried. POST .../projects/{project_url}/push. |
lingohub_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
lingohub_request_feature | Request a missing feature Tell usefulapi that the user needs something the Lingohub tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
lingohub_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Lingohub (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $39/month or $390/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
lingohub_cancel_subscription | Cancel the Pro subscription Cancel the caller's Lingohub Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run lingohub_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper API key | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this LingoHub server only. Subscribe with lingohub_upgrade (it returns a Stripe Checkout link). Cancel any time with lingohub_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running lingohub_upgrade before then undoes the cancel. Or write to [email protected].
Review translation progress. Inspect localization resources. Export current translations. Upload a reviewed resource file. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by LingoHub. The server calls the LingoHub API with your own LingoHub access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Lingohub API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Lingohub API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the LingoHub API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in LingoHub.
Yes, if you approve it. 6 of the 14 LingoHub tools can create or change data. The other 8 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this LingoHub server only. Cancel any time: Pro then runs to the end of the paid period. Run lingohub_usage_status to see how many calls you used.
Ask the AI to run lingohub_upgrade: it returns a Stripe Checkout link. To cancel, run lingohub_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with lingohub_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.