Connect
Optimize
Secure
Lokalise MCP Server
for AI Agents
Production-ready Lokalise MCP server with 101 extensible actions — plus built-in authentication, security, and optimized execution.
Lokalise MCP Server
Built by 
StackOne
StackOne 
Coverage
101 Agent Actions
Create, read, update, and delete across Lokalise — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Lokalise MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Lokalise tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Lokalise call.
Tools Discovery →What is the Lokalise MCP Server?
A Lokalise MCP server lets AI agents read and write Lokalise data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Lokalise MCP server ships with 101 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Lokalise MCP Tools and Actions
Every action from Lokalise's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Comments
- Create Comment
Add a comment to a translation key.
- Get Comment
Retrieve a specific comment.
- Delete Comment
Delete a comment from a translation key.
Contributors
- Create Contributors
Add contributors to a project.
- List Contributors
List all contributors in a project.
- Get Contributor
Retrieve a specific contributor from a project.
- Update Contributor
Update a contributor's role or language permissions.
- Delete Contributor
Remove a contributor from a project.
Custom Translation Status
- Create Custom Translation Status
Create a new custom translation status.
- Get Custom Translation Status
Retrieve a specific custom translation status.
- Update Custom Translation Status
Update a custom translation status.
- Delete Custom Translation Status
Delete a custom translation status.
Files
- Upload File
Upload a translation file to a project.
- List Files
List all files in a project.
- Download Files
Download all translation files from a project.
- Delete File
Delete a file from a project.
Glossary Terms
- Create Glossary Terms
Add glossary terms to a project.
- List Glossary Terms
List all glossary terms in a project.
- Get Glossary Term
Retrieve a specific glossary term.
- Update Glossary Terms
Update existing glossary terms.
- Delete Glossary Terms
Delete glossary terms from a project.
Keys
- Create Keys
Create one or more translation keys in a project.
- List Keys
List all translation keys in a project.
- Get Key
Retrieve a specific translation key by ID.
- Update Key
Update a translation key's properties.
- Delete Key
Delete a specific translation key.
Languages
- Create Languages
Add one or more languages to a project.
- Get Language
Retrieve a specific language from a project.
- Update Language
Update a language's settings in a project.
- Delete Language
Remove a language from a project.
Orders
- Create Order
Place a new professional translation order.
- List Orders
List all translation orders for a team.
- Get Order
Retrieve a specific translation order.
Payment Cards
- Create Payment Card
Add a new payment card.
- List Payment Cards
List all payment cards on file.
- Get Payment Card
Retrieve a specific payment card.
- Delete Payment Card
Remove a payment card from the account.
Projects
- Create Project
Create a new Lokalise project.
- List Projects
List all projects accessible to the authenticated user.
- Get Project
Retrieve details of a specific project.
- Update Project
Update an existing project's settings.
- Delete Project
Delete a project and all its data.
Screenshots
- Create Screenshots
Upload screenshots to a project.
- List Screenshots
List all screenshots in a project.
- Get Screenshot
Retrieve a specific screenshot.
- Update Screenshot
Update a screenshot's metadata or associated keys.
- Delete Screenshot
Delete a screenshot from a project.
Segments
- List Segments
List all segments for a key-language pair.
- Get Segment
Retrieve a specific segment.
- Update Segment
Update a specific translation segment.
Snapshots
- Create Snapshot
Create a snapshot (backup) of a project.
- List Snapshots
List all snapshots of a project.
- Delete Snapshot
Delete a project snapshot.
Tasks
- Create Task
Create a new translation task in a project.
- List Tasks
List all translation tasks in a project.
- Get Task
Retrieve a specific translation task.
- Update Task
Update a translation task's properties.
- Delete Task
Delete a translation task.
Teams
- List Teams
List all teams the authenticated user belongs to.
- Get Team
Retrieve details of a specific team.
Team Users
- List Team Users
List all users in a team.
- Get Team User
Retrieve a specific team user.
- Update Team User
Update a team user's role.
- Delete Team User
Remove a user from a team.
Groups
- Create Group
Create a new permission group in a team.
- List Groups
List all permission groups in a team.
- Get Group
Retrieve a specific permission group.
- Update Group
Update a permission group's name, rights, or language access.
- Delete Group
Delete a permission group from a team.
Translations
- List Translations
List all translations in a project.
- Get Translation
Retrieve a specific translation by ID.
- Update Translation
Update the value or status of a translation.
Translation Providers
- List Translation Providers
List all available translation providers for a team.
- Get Translation Provider
Retrieve details of a specific translation provider.
Webhooks
- Create Webhook
Create a new webhook for a project.
- List Webhooks
List all webhooks in a project.
- Get Webhook
Retrieve a specific webhook.
- Update Webhook
Update an existing webhook's configuration.
- Delete Webhook
Delete a webhook from a project.
Other (22)
- Create JWT Token
Create a service JWT token for OTA SDK authentication.
- Add Projects To Group
Add projects to a permission group.
- Add Members To Group
Add team users to a permission group.
- List Project Comments
List all comments across a project.
- List Key Comments
List all comments for a specific key.
- Get Current Contributor
Retrieve the contributor profile of the authenticated user.
- List Custom Translation Statuses
List all custom translation statuses in a project.
- Get Available Status Colors
Retrieve the list of available colors for custom translation statuses.
- Download Files (Async)
Asynchronously download translation files from a project.
- List System Languages
List all supported languages in the Lokalise system.
- List Project Languages
List all languages enabled in a project.
- List Permission Templates
List all permission templates available for a team.
- List Queued Processes
List all queued processes in a project.
- Get Queued Process
Retrieve the status of a specific queued process.
- Get User
Retrieve basic profile data for a user.
- Delete Multiple Keys
Delete multiple translation keys by IDs.
- Remove Projects From Group
Remove projects from a permission group.
- Remove Members From Group
Remove team users from a permission group.
- Multi-update Keys
Update multiple translation keys at once.
- Empty Project
Remove all keys and translations from a project.
- Restore Snapshot
Restore a project from a snapshot.
- Regenerate Webhook Secret
Regenerate the secret for a webhook.
Set Up Your Lokalise MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Lokalise in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Documents & Knowledge MCP Servers
Confluence
133+ actions
ClickUp
92+ actions
Discourse
67+ actions
Google Drive
47+ actions
JotForm
44+ actions
Figma
39+ actions
OneNote
37+ actions
Lokalise MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Lokalise MCP Server FAQ
Lokalise MCP server vs direct API integration — what's the difference?
A Lokalise MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Lokalise. A Lokalise MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Lokalise at runtime. StackOne provides both.
How does Lokalise authentication work for AI agents?
Lokalise authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Lokalise account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Lokalise MCP tools vulnerable to prompt injection?
Yes — Lokalise MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Lokalise agent and how do I avoid it?
Context bloat happens when Lokalise tool schemas and API responses eat your Lokalise agent's memory, preventing it from reasoning effectively. A single Lokalise query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Lokalise agent can access?
Yes — you can limit which actions your Lokalise agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Lokalise MCP server?
Yes — you can create custom agent actions for your Lokalise MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lokalise's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Lokalise MCP server?
Skip a Lokalise MCP server if your integration is purely software-to-software — direct Lokalise API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Lokalise actions at runtime.
What AI frameworks and AI clients does the StackOne Lokalise MCP server support?
The StackOne Lokalise MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.