Live 58 Actions

Lilt MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Lilt MCP server support?

The StackOne Lilt 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.

Connect your AI agent to StackOne's Lilt MCP server and give it 58 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Lilt MCP Server

Built by

StackOne

Coverage

58 Agent Actions

Create, read, update, and delete across Lilt — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Lilt MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Lilt 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 Lilt call.

Tools Discovery →

What is the Lilt MCP Server?

A Lilt MCP server lets AI agents read and write Lilt data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Lilt MCP server ships with 58 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Lilt MCP Tools

Every action from Lilt's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Lilt Create Contents

Retrieve Lilt Create Content
Retrieve all Lilt Create generated content.
Update Lilt Create Content
Update an existing Lilt Create content item.
Delete Lilt Create Content
Delete a Lilt Create content item by its ID.

A Documents

Upload A Document
Upload a file as a Document into a Project.
Download A Document
Download a Document by its unique identifier.

A Files

Upload A File
Upload a source file to Lilt.
Download A File
Download a source file by its ID.
Delete A File
Delete a source file by its unique identifier.

A Jobs

Create A Job
Create a new translation Job.
Retrieve A Job
Retrieve a single Job by its unique identifier.
Download A Job
Download the translated files for a Job.
Export A Job
Export files or memory for a Job.
Update A Job
Update an existing Job.
Delete A Job
Delete a Job by its unique identifier.

A Memorys

Create A Memory
Create a new Memory for a specific source/target language pair.
Query A Memory
Query a Memory for translation memory matches to a source string.
Update A Memory
Update the name of an existing Memory.
Delete A Memory
Delete a Memory by its unique identifier.

A Termbases

Download A Termbase
Download the termbase for a Memory.
Export A Termbase
Start an export of the termbase for a Memory.

A Projects

Create A Project
Create a new translation Project.
Delete A Project
Delete a Project by its unique identifier.

A Segments

Create A Segment
Create a new Segment in a Memory or Document.
Retrieve A Segment
Retrieve a single Segment by its unique identifier.
Update A Segment
Update the target string of a Segment.
Delete A Segment
Delete a Segment by its unique identifier.

Other (32)

Add A Label To A File
Add a label to a source file.
Import A File Into A Memory
Import a translation memory or termbase file into an existing Memory.
Retrieve Lilt Create Content By ID
Retrieve a single Lilt Create content item by its ID.
Retrieve Domains
Retrieve the translation domains configured for your Lilt organization.
Retrieve Files
Retrieve source files, optionally filtered by ID or labels.
Retrieve All Jobs
Retrieve all Jobs, optionally filtered by archived/delivered status.
Retrieve Job Leverage Stats
Retrieve translation leverage statistics for a Job.
Retrieve Supported Languages
Retrieve the list of source and target languages supported by Lilt.
Retrieve Memories
Retrieve all Memories, or a single Memory by ID.
Retrieve Projects
Retrieve Projects, optionally filtered by language, state, or time.
Download A Translated File
Download the result of a completed file translation.
Retrieve Pending Uploads
Retrieve all pending uploads, optionally filtered by IDs or statuses.
Retrieve An Upload
Retrieve a single upload by its unique identifier.
Retrieve S3 Upload Parameters
Get the parameters needed to upload a file directly to cloud storage.
Retrieve Workflow Templates
Retrieve the workflow templates available to your Lilt organization.
Remove A Label From A File
Remove a label from a source file.
Delete A Segment From A Memory
Remove a specific segment from a Memory.
Generate Lilt Create Content
Generate new content with Lilt Create.
Archive A Job
Archive a Job by its unique identifier.
Unarchive A Job
Unarchive a previously archived Job.
Deliver A Job
Mark a Job as delivered.
Reactivate A Job
Reactivate a delivered Job.
Tag A Segment
Transfer inline tags from a tagged source string to a target string.
Unlock Segments
Unaccept and unlock one or more segments.
Translate A Segment
Translate a source string using adaptive machine translation.
Translate A File
Start an instant machine translation of one or more uploaded files.
Monitor File Translation
Check the status of one or more file translations.
Initiate File Upload To Cloud Storage
Initiate a single-part file upload to cloud storage.
Initiate Multipart Upload
Initiate a multipart file upload to cloud storage.
Sign An Upload Part
Get a signed URL for uploading a single part of a multipart upload.
Complete Multipart Upload
Complete a multipart upload after all parts have been uploaded.
Cancel Multipart Upload
Cancel an in-progress multipart upload.

Set Up Your Lilt MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Lilt in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "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>"
      ]
    }
  }
}

Platform 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

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Lilt MCP Server FAQ

Does StackOne have a Lilt MCP server?

Yes. StackOne offers a hosted Lilt MCP server with 58 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Lilt MCP server vs direct API integration — what's the difference?

A Lilt MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Lilt. A Lilt 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 Lilt at runtime. StackOne provides both.

How does Lilt authentication work for AI agents?

Lilt 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 Lilt account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Lilt MCP tools vulnerable to prompt injection?

Yes — Lilt 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 Lilt agent and how do I avoid it?

Context bloat happens when Lilt tool schemas and API responses eat your Lilt agent's memory, preventing it from reasoning effectively. A single Lilt 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 Lilt agent can access?

Yes — you can limit which actions your Lilt 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 Lilt MCP server?

Yes — you can create custom agent actions for your Lilt MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lilt's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Lilt MCP server?

Skip a Lilt MCP server if your integration is purely software-to-software — direct Lilt 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 Lilt actions at runtime.

What AI frameworks and AI clients does the StackOne Lilt MCP server support?

The StackOne Lilt 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.

Start Free Book Demo

Lilt MCP Serverfor AI Agents