Integration

conv2pdf integration

conv2pdf converts and edits PDF files on servers in France: convert Word, Excel, PowerPoint, OpenDocument and Apple Pages documents, images, iPhone HEIC photos, EPUB e-books, PostScript and HTML files or a public web page address to PDF; convert a PDF to Word or to images; and merge, split, extract pages from, compress, rotate, password-protect, unlock, watermark or number PDFs. Each conversion tool takes a file from a previous step and returns a job_id; download_job_file then returns the result as a file, which conv2pdf deletes one hour after the conversion (delete_job erases it sooner). list_tools gives the accepted formats and file counts, and get_quota the account's plan and usage, both free. Authentication is an API key (starts with cpdf_live_) sent as a Bearer token, created in the Developer tab of the conv2pdf dashboard and shown only once. Every conversion counts against the account's quota (the Dev plan includes 300 trial conversions valid 12 months, 10 MB per file; paid plans renew monthly, 200 MB per file), at most 20 conversions per minute per key.

Connect conv2pdf How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in conv2pdf.Built from the 24 conv2pdf tools below, on the connection you add once.

What you can do with conv2pdf

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

Pdf, 9 operations

add_pdf_page_numbersAdd pdf page numbersPOSTAgents: ask firstNumbers the pages of a PDF at the bottom (center, left or right), with or without the total page count. Returns job_id: download it with download_job_file. Counts one conversion.
compress_pdfCompress pdfPOSTAgents: ask firstReduces the size of a PDF by resampling its images to 72, 150 or 300 DPI (quality low, medium or high). Returns job_id: download it with download_job_file. Counts one conversion.
extract_pdf_pagesExtract pdf pagesPOSTAgents: ask firstKeeps the chosen pages of a PDF, in the order written, in a new single PDF (ranges such as 1-5,7,10-12). Returns job_id: download it with download_job_file. Counts one conversion.
merge_pdfsMerge pdfsPOSTAgents: ask firstMerges 2 to 20 PDFs into one, in the order file_1, file_2, ... (2 files on the Dev plan, up to 20 on paid plans). Returns job_id: download it with download_job_file. Counts one conversion.
protect_pdfProtect pdfPOSTAgents: ask firstEncrypts a PDF with a password (AES-256), optionally forbidding printing or copying text. Returns job_id: download the protected copy with download_job_file. Counts one conversion.
rotate_pdfRotate pdfPOSTAgents: ask firstRotates every page of a PDF clockwise by 90, 180 or 270 degrees. Returns job_id: download it with download_job_file. Counts one conversion.
split_pdfSplit pdfPOSTAgents: ask firstSplits a PDF into one PDF per page (page-001.pdf, page-002.pdf, ...), delivered in a ZIP file. To keep chosen pages in one PDF, use extract_pdf_pages instead. Counts one conversion.
unlock_pdfUnlock pdfPOSTAgents: ask firstRemoves the password and the printing or copying restrictions from a PDF whose password you know. Returns job_id: download the unlocked copy with download_job_file. Counts one conversion.
watermark_pdfWatermark pdfPOSTAgents: ask firstStamps a text watermark (up to 50 characters, such as CONFIDENTIAL) on every page of a PDF. Returns job_id: download it with download_job_file. Counts one conversion.

Pdf conversion, 7 operations

convert_epub_to_pdfConvert epub to pdfPOSTAgents: ask firstConverts an EPUB e-book to a PDF on A4 pages, with its table of contents and internal links. Returns job_id: download it with download_job_file. Counts one conversion.
convert_heic_to_pdfConvert heic to pdfPOSTAgents: ask firstConverts one iPhone HEIC or HEIF photo to a PDF. Returns job_id: download the PDF with download_job_file. Counts one conversion.
convert_html_to_pdfConvert html to pdfPOSTAgents: ask firstConverts an HTML file to PDF as it prints in a browser (print stylesheet): selectable text, clickable links. Returns job_id: download it with download_job_file. Counts one conversion.
convert_image_to_pdfConvert image to pdfPOSTAgents: ask firstConverts one PNG, JPG, WEBP, GIF or TIFF image to a PDF. Returns job_id: download the PDF with download_job_file. Counts one conversion.
convert_office_to_pdfConvert office to pdfPOSTAgents: ask firstConverts a Word, Excel, PowerPoint, OpenDocument, RTF, TXT, CSV or Apple Pages file to PDF. Returns job_id: download the PDF with download_job_file. Counts one conversion.
convert_postscript_to_pdfConvert postscript to pdfPOSTAgents: ask firstConverts a PostScript (.ps) or EPS file to PDF, text kept as text and drawings as vectors. Returns job_id: download it with download_job_file. Counts one conversion.
convert_url_to_pdfConvert url to pdfPOSTAgents: ask firstConverts the public web page at an http or https address to PDF, as it prints in a browser. Takes no file. Returns job_id: download it with download_job_file. Counts one conversion.

Conversion job, 2 operations

delete_jobDelete jobDELETEAgents: ask firstPermanently deletes a conversion job and its result file right away, without waiting for the automatic deletion one hour after the conversion. The job then answers HTTP 410 job_deleted.
get_jobGet jobGETAgents: ask firstReturns the status and metadata of a successful conversion job: tool, result size, completion and expiry times and download path. A job with no output answers HTTP 409 job_not_ready; a deleted one 410.

Image conversion, 2 operations

convert_heic_to_jpgConvert heic to jpgPOSTAgents: ask firstConverts one iPhone HEIC or HEIF photo to a JPG image. Returns job_id: download the JPG with download_job_file. Counts one conversion.
convert_pdf_to_imagesConvert pdf to imagesPOSTAgents: ask firstRenders each page of a PDF as a PNG or JPG image at 150 DPI, delivered in one ZIP file. Returns job_id: download the ZIP with download_job_file. Counts one conversion.

Conversion result, 1 operation

download_job_fileDownload job fileGETAgents: ask firstDownloads the result of a conversion job as a file (PDF, DOCX, JPG or ZIP depending on the tool), from its job_id. Available for one hour after the conversion; then HTTP 410 file_expired.

Conversion tool, 1 operation

list_toolsList toolsGETAgents: ask firstLists the 19 conversion tools with, for each, its identifier, the minimum and maximum number of input files and the accepted file extensions. Answers without spending a conversion.

Quota, 1 operation

get_quotaGet quotaGETAgents: ask firstReturns the account's quota state: plan, conversions included and used, overage cap, status (ok, soft_cap, hard_cap) and reset or expiry dates. Free, no side effect; also answers when conversions are refused.

Word conversion, 1 operation

convert_pdf_to_wordConvert pdf to wordPOSTAgents: ask firstConverts a PDF that contains real text to an editable Word (.docx) document. Scanned PDFs are refused (no OCR in the API). Returns job_id: download it with download_job_file.

Use conv2pdf from Claude Code, Cursor or Codex

Connect conv2pdf in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its conv2pdf 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 conv2pdf

Create your workspace
Sign up free. Nothing to install.
Connect conv2pdf once
Add your conv2pdf 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.