Skip to main content
Glama
TotersLokalise MCP Server

TotersLokalise MCP Server

by toters-eng

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TOTERSLOKALISE_SECRETYesThe one-time secret associated with the API credential (e.g. gl_secret_…).
TOTERSLOKALISE_ACCESS_KEYYesThe organization API credential access key (e.g. gl_live_…) created under Settings → Developer → API credentials.
TOTERSLOKALISE_API_ORIGINNoThe TotersLokalise API origin to connect to. Set this to use another deployment, for example http://localhost:3000 when running the TotersLokalise backend locally.https://arcade.stage.toters-api.com/toters-lokalise

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
toterslokalise_list_projectsB

List active Lingo Rider projects visible to the scoped organization credential.

toterslokalise_export_translationsC

Read translations from one project/environment. Published translations are returned by default.

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.

toterslokalise_analyze_importA

Analyze up to 20 localization files without changing translations. Review the returned session and conflicts before calling proceed.

toterslokalise_get_import_sessionB

Poll a durable import analysis or import job and read its immutable hashes and counts.

toterslokalise_list_import_itemsB

Page through analyzed import items. Use classification=conflict to collect every decision required before proceeding.

toterslokalise_proceed_importB

WRITE ACTION: apply one previously analyzed import snapshot. Every review-policy conflict must have an explicit resolution.

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.

toterslokalise_cancel_importB

Cancel an import session that has not completed. This never deletes translations already committed by another completed session.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 9 tools

Disambiguation4/5

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).

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness3/5

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

ActivityMaintained
ResponsivenessOutdated data