TotersLokalise MCP Server
Exports translations as Android XML string resources for Android app localization.
Exports translations as Apple .strings files for iOS/macOS localization, alongside the other export formats.
Pairs with the Figma MCP server in the same agent so design text layers can be read from a Figma frame and created as TotersLokalise keys with their per-locale values (e.g. English text), including a dry run before writing.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TotersLokalise MCP Server list my TotersLokalise projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Lingo Rider MCP server
The official Model Context Protocol server
for Lingo Rider (technical name toterslokalise). It lets Cursor, Claude, and other MCP hosts discover projects,
download app-ready translation files, and run the same reviewed import workflow as the dashboard.
Every call uses one organization API credential and its explicit scopes — it
never bypasses Lingo Rider authorization.
Quick start
In Lingo Rider, open Workspace administration → API credentials and create a dedicated credential. Copy the access key and the one-time secret.
Add this to your MCP host configuration (Cursor, Claude Desktop, Claude Code, or any stdio MCP host):
{
"mcpServers": {
"toterslokalise": {
"command": "npx",
"args": ["-y", "@totersapp/toterslokalise-mcp"],
"env": {
"TOTERSLOKALISE_ACCESS_KEY": "gl_live_…",
"TOTERSLOKALISE_SECRET": "gl_secret_…"
}
}
}
}Ask your assistant to list your Lingo Rider projects.
npx installs the published @totersapp/toterslokalise-mcp package (Node.js 20.19+).
The server connects to the Lingo Rider API at
https://arcade.stage.toters-api.com/toters-lokalise by default. Set
TOTERSLOKALISE_API_ORIGIN to use another deployment, for example
http://localhost:3000 when running the Lingo Rider backend locally.
Related MCP server: opencode-mcp
Credentials and scopes
Scope | Grants |
| List projects in the credential organization. |
| Read translations and import sessions. |
| Export app files: iOS, Android, PHP, JSON, xcstrings, CSV, Excel. |
| Analyze, approve, and cancel durable import sessions. |
| Add or change source-language (English) text. Owners only. |
Use only projects:read, translations:read, and exports:read for read-only
agents. Add imports:write only when the agent must import translations.
Production imports remain disabled and must go through promotion. Never use a
dashboard session credential here, and never commit or share the secret.
Tools
toterslokalise_list_projects— discover projects (paged).toterslokalise_export_files— download app-ready files, the same as the Export screen: iOS.strings/.stringsdict, Androidstrings.xml, PHP, JSON, xcstrings, CSV or Excel, every language at once, with{0}placeholders converted (%@on iOS,%son Android). PassoutputDir(relative to the current project, e.g.ios/Resources) to write the files, ZIPs unpacked; without it the text files are returned for review. Options match the export screen:locales,namespaces,tags,fileNamepattern,missing,keyCase,keyQuotes,statuses(published by default). Needsexports:read.toterslokalise_export_translations— read filtered translations as JSON,.stringsor XML (one language per call, placeholders as written).toterslokalise_analyze_import— analyze up to 20 files without changing data.toterslokalise_get_import_session— poll a durable import session.toterslokalise_list_import_items— page through analyzed items.toterslokalise_proceed_import— apply an approved analysis (write action).toterslokalise_cancel_import— cancel a session before approval.toterslokalise_create_keys— create keys with their text in one call (write action), for example keys and strings read from a Figma design by the Figma MCP server. Values are per locale ({ "en-US": "Pay now" }); existing text is kept unlessexistingValues: "overwrite";dryRun: truepreviews. Needsimports:write, plussource:writeto write English. The result counts values (one key in one language):new,updated,unchanged, andconflicts(existing text that differs), withexistingTextsaying whether that text waskeptoroverwritten.
Figma → Lingo Rider
Connect both the Figma MCP server and this one in the same agent, then ask, for
example: "Read the Checkout frame in Figma, list each text layer with its key
name, and create those keys in Lingo Rider project <id> (namespace
checkout) with the English text. Do a dry run first."
Single sign-on (Okta)
The MCP server calls /api/v1/* directly with the credential. If that path is
behind Okta, every call fails with "answered by a sign-in page": the platform
team must exempt /toters-lokalise/api/v1/* from Okta (the API checks the
credential itself).
Analysis never mutates translations. Approval requires the server-issued
analysisHash and projectStateHash plus a decision for every review-policy
conflict, so a stale or partial snapshot cannot be applied.
Full documentation, including Cursor and Claude setup, the analyze/approve/apply workflow, and troubleshooting: the API & MCP reference in Lingo Rider (Developer Hub → API reference).
Releasing
npm version 0.3.1 --tag-version-prefix=""
git push origin main 0.3.1The Release workflow tests the tag and publishes it to npmjs.com.
Available Tools
9 toolstoterslokalise_analyze_importA
Analyze up to 20 localization files without changing translations. Review the returned session and conflicts before calling proceed.
Inputs: files (required), projectId (required), tags, environment, +1 more.
toterslokalise_cancel_importB
Cancel an import session that has not completed. This never deletes translations already committed by another completed session.
Inputs: projectId (required), sessionId (required), environment.
toterslokalise_create_keysA
WRITE ACTION: create translation keys with their text, e.g. keys and strings read from a Figma design. Values are keyed by locale (use the project languages, e.g. en-US, ar-LB). Existing text is kept unless existingValues is "overwrite". New translations land as drafts in the chosen environment. Use dryRun first to preview. Writing source-language (English) text needs a credential with the source:write scope.
Inputs: keys (required), projectId (required), tags, dryRun, +3 more.
toterslokalise_export_filesA
Download app-ready translation files, the same as the Export screen: iOS .strings/.stringsdict, Android strings.xml, PHP, JSON, xcstrings, CSV or Excel, with {0} placeholders converted (%@ on iOS, %s on Android) and every language in one go. With outputDir the files are written (ZIPs unpacked) into that folder of the current project, e.g. "ios/Resources"; without it, text files are returned for review.
Inputs: format (required), projectId (required), tags, keyCase, +12 more.
toterslokalise_export_translationsC
Read translations from one project/environment. Published translations are returned by default.
Inputs: projectId (required), keys, tags, format, +4 more.
toterslokalise_get_import_sessionB
Poll a durable import analysis or import job and read its immutable hashes and counts.
Inputs: projectId (required), sessionId (required), environment.
toterslokalise_list_import_itemsB
Page through analyzed import items. Use classification=conflict to collect every decision required before proceeding.
Inputs: projectId (required), sessionId (required), limit, cursor, +2 more.
toterslokalise_list_projectsB
List active Lingo Rider projects visible to the scoped organization credential.
Inputs: limit, cursor.
toterslokalise_proceed_importB
WRITE ACTION: apply one previously analyzed import snapshot. Every review-policy conflict must have an explicit resolution.
Inputs: projectId (required), sessionId (required), analysisHash (required), projectStateHash (required), +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
The import cluster (analyze_import, get_import_session, list_import_items, proceed_import, cancel_import) has clearly separated roles described in lifecycle terms, and create_keys is distinct as the only key-writing tool. The only real overlap is export_translations vs export_files, which both read translations but differ in output form (raw data vs app-ready files).
Every tool uses the same toterslokalise_ namespace prefix followed by a snake_case verb_noun pattern (list_projects, export_files, analyze_import, proceed_import, cancel_import). No mixed casing or inconsistent verb styles.
Nine tools sit in the well-scoped 3-15 range and each maps to a real step: project discovery, two export paths, a multi-step import workflow, key creation, and import cancellation. Nothing appears redundant or padding.
Read/export and import workflows are well covered, but the write surface is thin: there is no update of existing translation text (only create_keys with an overwrite flag) and no delete of keys or translations, which are core operations in a translation-management domain. Listing languages/environments or project metadata is also absent, leaving agents with dead ends for common edits.
Maintenance
Related MCP Connectors
Official MCP server for POEditor, the translation management system. Hosted, OAuth 2.1.
One MCP endpoint for your company's tools, with per-person sign-in, policy and audit.
Discover, plan and run tools across your connected business systems through one OAuth MCP endpoint
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables clients such as Claude, Cursor, VS Code, and Windsurf to manage workspaces, projects, tasks, and AI agents through a hosted OAuth endpoint or a local stdio package, and to generate MCP tools from OpenAPI specs.2,530 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients such as Claude, Cursor, and VS Code to delegate coding tasks to OpenCode, including asking questions, implementing features, monitoring background work, handling prompts and permissions, and reviewing changes across projects.23,789 npmMIT
- AlicenseBqualityBmaintenanceEnables MCP clients such as Claude and Cursor to invoke one tool per API operation for campaign management, audience import/export, conversation replies, account login jobs, and media uploads with scoped authentication.4932 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to discover and execute hosted project-management tools through one PipMCP API key, including reading work items and applying explicitly approved changes under policy controls.MIT