Integration

Carbone integration

Carbone Cloud generates documents (PDF, DOCX, XLSX, PPTX, ODT, HTML, images and more) by merging a stored template that contains Carbone tags such as {d.field} with a JSON dataset, and converts documents between 100+ formats. Upload, list, download, update and delete templates and their versions, list template categories and tags, generate a document from a template, and convert a base64 document in one call; generated files are returned directly as files. Asynchronous rendering with webhook callbacks, batch generation (which needs a webhook) and the separate download-by-render-id step are not exposed, and the PDF, image and CSV option objects of convertTo are not available. Generations are billed per document on the production key (the free plan includes 100 documents a month; extra documents past the plan quota cost 0.05 EUR on Free, 0.02 EUR on Essential, down to 0.001 EUR on the largest plans; the test key renders unlimited watermarked PDFs only), and the synchronous render times out after 60 seconds. Authentication is a Carbone API key (test or production, from the Carbone account home page) sent as a Bearer token in the Authorization header; the carbone-version header is fixed to 5.

Connect Carbone How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Carbone.Built from the 10 Carbone tools below, on the connection you add once.

What you can do with Carbone

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.

Template, 5 operations

delete_templateDelete templateDELETEDeletes a template with all its versions (Template ID) or one version (Version ID), for real: it stops being listed or usable at once and the file is removed after 24 hours on Carbone Cloud.
download_templateDownload templateGETDownloads a stored template file (the deployed version for a Template ID, or one exact version for a Version ID) and returns it as a file.
list_templatesList templatesGETLists stored templates (deployed versions by default, newest first, expired ones excluded) with id, versionId, name, category, tags and dates. Pages with cursor: pass nextCursor while hasMore is true.
update_templateUpdate templatePATCHUpdates a template's metadata (name, comment, category, tags, expiration, deployment) without re-uploading it. A Template ID patches its deployed version; a Version ID patches that version. Only the fields sent change.
upload_templateUpload templatePOSTUploads a template file (DOCX, XLSX, PPTX, ODT, ODS, ODP, ODG, XHTML, IDML, HTML or XML) to Carbone storage and returns its Template ID and Version ID. Set versioning true to get a Template ID that keeps versions.

Document, 2 operations

convert_documentConvert documentPOSTConverts a base64 document to another format and returns the file. Acts for real: one billed document per call (more above 1 MB of data); extras past the plan quota cost 0.05 EUR (Free) to 0.001 EUR. Test key: free watermarked PDFs.
generate_documentGenerate documentPOSTMerges a stored template (Template ID from list_templates) with JSON data and returns the file. Acts for real: one billed document per call (more above 1 MB of data); extras 0.05 EUR (Free) to 0.001 EUR. Test key: free watermarked PDFs.

Status, 1 operation

get_statusGet statusGETReturns the Carbone API status and server version. Needs no API key.

Template category, 1 operation

list_template_categoriesList template categoriesGETLists the category names used by deployed templates, sorted by name, to pass as category to list_templates or upload_template.

Template tag, 1 operation

list_template_tagsList template tagsGETLists the tag names used by deployed templates, sorted by name. Templates cannot be filtered by tag.

Use Carbone from Claude Code, Cursor or Codex

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

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