Integration

AI21 Labs integration

AI21 Labs Studio API for Jamba large language models (jamba-large, jamba-mini), document-grounded conversational RAG, AI21 Maestro orchestrated runs, and the file Library used for retrieval-augmented generation. Supports OpenAI-compatible chat completions with tools, structured JSON output, server-sent events streaming, and library file management (upload, list, get, update, delete, download link).

Connect AI21 Labs How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AI21 Labs.Built from the 11 AI21 Labs tools below, on the connection you add once.

Common AI21 Labs use cases

conversational AI
real-time chat UI
auditing RAG corpus
research assistants
retagging documents
GDPR right-to-erasure
polling upload status
RAG knowledge ingestion
knowledge base assistant
polling agent completion

What you can do with AI21 Labs

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Library file, 6 operations

delete_library_fileDelete library fileDELETEPermanently removes a file from the AI21 Library.
get_library_fileGet library fileGETFetches metadata for a single AI21 Library file by id.
get_library_file_download_linkGet library file download linkGETIssues a short-lived signed URL for downloading the raw bytes of an AI21 Library file.
list_library_filesList library filesGETLists files in the AI21 Library with optional filtering on name, status, or labels and offset/limit pagination.
update_library_fileUpdate library filePUTUpdates labels or publicUrl metadata on an existing AI21 Library file.
upload_library_fileUpload library filePOSTUploads a document to the AI21 Library for use as RAG context. Returns the new file id.

Chat completion, 2 operations

chat_completionsChat completionsPOSTGenerates a chat completion with an AI21 Jamba model (jamba-large or jamba-mini) given a conversation history. Supports function calling via tools, JSON-mode output, multiple choices (n), custom stop sequences, and document grounding. Returns the ...
chat_completions_streamChat completions streamPOSTStreams a chat completion from an AI21 Jamba model as Server-Sent Events newline-delimited chunks. Each chunk carries an incremental assistant content delta; the terminal chunk carries the finish_reason and token usage. Requires n=1 and is incompa...

Maestro run, 2 operations

maestro_create_runMaestro create runPOSTStarts an AI21 Maestro run - a planner-orchestrator agent over Jamba with file_search/web_search/HTTP/MCP tools. Returns a run id; poll maestro_retrieve_run for completion.
maestro_retrieve_runMaestro retrieve runGETFetches the status and (when ready) the result of an AI21 Maestro run.

Conversational rag, 1 operation

conversational_ragConversational ragPOSTAnswers a chat turn grounded in documents from the AI21 Library. Retrieves relevant segments using hybrid (dense + keyword) search, optionally filtered by file_ids, labels, or path, and passes them to a Jamba model to produce a cited answer. Depre...

Use AI21 Labs from Claude Code, Cursor or Codex

Connect AI21 Labs in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AI21 Labs operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect AI21 Labs

Create your workspace
Sign up free. Nothing to install.
Connect AI21 Labs once
Add your AI21 Labs connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

AI21 Labs integration FAQ

What can you do with the AI21 Labs integration?

LiveContext exposes 11 operations on AI21 Labs, covering library file, chat completion, maestro run and conversational rag. Common uses include conversational AI, real-time chat UI and auditing RAG corpus.