Lokalise Integration for AI Agents
Connect your AI agent to 111 QA'd Lokalise actions via MCP, A2A, or SDK, with agent authentication, tool-calling execution, and security built-in, plus 33 events to subscribe to.
Lokalise AI Agent Actions
111 production-ready actions for your agent to do more on Lokalise.
Lokalise Webhook Events
33 real-time Lokalise events your AI agent can subscribe to.
- Active Check Responds with 200 OK to the Lokalise ping and to any delivery that does not match a known event.
- Project Imported Fired when a translation file is uploaded to a project (project.imported).
- Project Exported Fired when translation files are downloaded from a project (project.exported).
- Project Copied Fired when a project is copied (project.copied).
- Project Snapshot Created Fired when a project snapshot is created (project.snapshot).
- Branch Added Fired when a project branch is created (project.branch.added).
- Branch Deleted Fired when a project branch is deleted (project.branch.deleted).
- Branch Merged Fired when a project branch is merged into another branch (project.branch.merged).
- Languages Added Fired when one or more languages are added to a project (project.languages.added).
- Language Removed Fired when a language is removed from a project (project.language.removed).
- Language Settings Changed Fired when a project language's settings are changed (project.language.settings_changed).
- Key Added Fired when a single translation key is added to a project (project.key.added).
- Keys Added (Bulk) Fired when keys are added to a project in bulk, by file upload, or by copy or move (project.keys.added).
- Key Modified Fired when a single translation key is modified (project.key.modified).
- Keys Modified (Bulk) Fired when keys are modified by a bulk action, a replace, a file upload or an API call (project.keys.modified).
- Keys Deleted Fired when keys are deleted from a project, individually, in bulk, by a move or through the API (project.keys.deleted).
- Key Comment Added Fired when a comment is added to a translation key (project.key.comment.added).
- Translation Updated Fired when a single translation is modified (project.translation.updated).
- Translations Updated (Bulk) Fired when translations are modified in bulk, for example by translation memory, machine translation or a file upload (project.translations.updated).
- Translation Reviewed Fired when a translation is marked or unmarked as reviewed (project.translation.proofread).
- Translations Reviewed (Bulk) Fired when several translations are marked or unmarked as reviewed at once, for example through an API multicall (project.translations.proofread).
- Contributor Added Fired when an admin adds a contributor to a project (project.contributor.added).
- Contributor Joined via Public Link Fired when a contributor adds themselves to a project through the public signup link (project.contributor.added_public).
- Contributor Removed Fired when a contributor is removed from a project (project.contributor.deleted).
- Task Created Fired when a translation or review task is created (project.task.created).
- Task Queued Fired when a new review task is queued behind an unfinished parent task or translation order (project.task.queued).
- Task Closed Fired when a task is closed, manually by an admin or automatically on completion (project.task.closed).
- Task Deleted Fired when a task is deleted (project.task.deleted).
- Task Language Closed Fired when one language of a task is closed, manually or on completion (project.task.language.closed).
- Task TM Leverage Calculated Fired when Lokalise finishes calculating the initial translation memory leverage for a task (project.task.initial_tm_leverage.calculated).
- Order Created Fired when a professional translation order is created (team.order.created).
- Order Deleted Fired when a translation order is deleted (team.order.deleted).
- Order Completed Fired when a translation order is marked completed (team.order.completed).
Do More, Build Less
Integration Infrastructure for Lokalise AI Agents
"What impressed us most about StackOne is its ambition and clarity. They're creating infrastructure that modern software and the entire AI agent ecosystem can rely on. The depth of secure integrations, the pace of delivery, and the team's foresight into AI's future uniquely position StackOne to redefine this category."
Luna Schmid, Partner at GV
"We've been impressed by how quickly and deeply StackOne integrates with complex enterprise systems -- and now, with their focus on agent-to-agent interoperability, they're unlocking even more powerful use cases for customers. StackOne delivers all of the above in a universal layer -- without compromise."
Barbry McGann, SVP at Workday Ventures
Lokalise AI agent integration resources
Webhooks for AI agents: why agentic workflows need them purpose-built
AI agents can act the moment a system changes, using webhooks. But webhooks built for software hit three limits in agentic workflows. Here is how to fix each.
7 min read
Agentic Context Engineering: Why AI Agents Kill Their Own Context Windows
AI agents exceed their context windows without knowing it. Six failure patterns and seven survival architectures for agentic context engineering.
15 min
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
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.