Integration

nele.ai integration

nele.ai is a German, GDPR-focused AI workspace for companies. Generate chat completions with the models enabled for your team (optionally grounded in a knowledge base or a web search), generate images, transcribe audio, and build knowledge bases (document collections): create and update them, upload files or import web pages as items, embed them and run semantic searches. Chat, image, transcription and search calls spend credits from your organisation's monthly AI volume (the cost of each call is returned in usage.credits) and fail with HTTP 402 once the credit limit is reached; knowledge bases are a paid add-on, and without it those calls fail with HTTP 422 'Module not enabled'. Rate limits are not published: an exceeded quota answers HTTP 429 'Too Many Attempts.', with X-Ratelimit-Limit, X-Ratelimit-Remaining and X-Ratelimit-Reset headers in the response. The streamed (SSE) chat completion, the raw image download and the saved-prompts store (it carries a write token) are not exposed. Authentication is an API key created in your nele.ai account, sent as a Bearer token.

Connect nele.ai How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in nele.ai.Built from the 19 nele.ai tools below, on the connection you add once.

What you can do with nele.ai

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.

Document collection, 7 operations

create_document_collectionCreate document collectionPOSTCreates a document collection (knowledge base), assigned to the API key owner. Returns its id; add items with upload_document_collection_item or import_document_collection_item_from_url. Needs the knowledge-base add-on.
delete_document_collectionDelete document collectionDELETEPermanently deletes a document collection and its items. This cannot be undone.
embed_document_collectionEmbed document collectionPUTStarts embedding, in the background, every item of the collection that can still be embedded, so it becomes searchable. Returns nothing; check progress with list_document_collection_items.
get_document_collectionGet document collectionGETReturns one document collection: title, description, enabled state and models, chunking settings and your permissions on it.
list_document_collectionsList document collectionsGETLists the document collections (knowledge bases) you can see, a page at a time, with item counts and your permissions. Page with current_page while it is below lastPage.
search_document_collectionSearch document collectionPOSTSemantic search in a knowledge base, returning matching snippets. Spends credits (usage.credits).
update_document_collectionUpdate document collectionPUTChanges a document collection's title, description, enabled state or enabled models. The docs do not say whether fields left out are kept: read it with get_document_collection first and send the values back.

Document collection item, 6 operations

delete_document_collection_itemDelete document collection itemDELETEPermanently deletes one item from its document collection. This cannot be undone.
embed_document_collection_itemEmbed document collection itemPUTStarts embedding one document collection item in the background, so it becomes searchable. Returns nothing; follow it with get_document_collection_item.
get_document_collection_itemGet document collection itemGETReturns one document collection item: title, type, status and last update time. Use it to follow an upload, an import or an embedding.
import_document_collection_item_from_urlImport document collection item from urlPOSTAdds a web page to a document collection: nele.ai fetches the url in the background. Returns the item id; poll get_document_collection_item for its status.
list_document_collection_itemsList document collection itemsGETLists the items (documents and imported pages) of a document collection, a page at a time, with their status and embedding progress. Page with currentPage while it is below lastPage.
upload_document_collection_itemUpload document collection itemPOSTUploads a file into a document collection. With auto_embed true it is embedded in the background (poll get_document_collection_item); otherwise call embed_document_collection_item. Returns the item id.

Audio, 1 operation

transcribe_audioTranscribe audioPOSTTranscribes an audio file into text. Spends credits (usage.credits).

Chat completion, 1 operation

create_chat_completionCreate chat completionPOSTGenerates a chat answer with one of the team's models and returns it whole. Spends credits (usage.credits).

Image, 1 operation

generate_imageGenerate imagePOSTGenerates an image from a prompt and returns a temporary url. Spends credits (usage.credits).

Image attachment, 1 operation

upload_image_attachmentUpload image attachmentPOSTUploads a png, jpg or webp image for use as a chat message attachment.

Model, 1 operation

list_modelsList modelsGETLists the AI models, team models, document collections and image generators your account can use, with is_usable and the credit consumption of each model. Read model ids here before chatting.

Settings, 1 operation

get_settingsGet settingsGETReturns the API key owner's settings: interface locale and default model name (empty when none is set).

Use nele.ai from Claude Code, Cursor or Codex

Connect nele.ai in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its nele.ai 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 nele.ai

Create your workspace
Sign up free. Nothing to install.
Connect nele.ai once
Add your nele.ai 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.