Conv2pdf
Summary: This MCP server uses the Conv2pdf API to convert files to PDF and perform common PDF editing tasks.
Convert Word, Excel, PowerPoint, OpenDocument, Pages, RTF, TXT, CSV, images, and EPUB files to PDF.
Convert iPhone HEIC/HEIF photos to JPG.
Convert text-based PDFs to editable Word DOCX files.
Convert PDF pages to PNG or JPG images in a ZIP archive.
Merge multiple PDFs into one.
Extract selected pages from a PDF.
Rotate all PDF pages clockwise by 90, 180, or 270 degrees.
Add page numbers with configurable format and position.
Add a text watermark to every page.
Compress PDFs by lowering image resolution.
Protect PDFs with a password and optionally block printing or copying.
Unlock PDFs when the password is known or remove restrictions.
Check the API plan, usage, and remaining quota.
Processing for PDF conversions runs on OVHcloud servers in France, keeping document processing within the EU.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Conv2pdf merge invoice1.pdf and invoice2.pdf, then compress the result"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
conv2pdf-mcp
Official Model Context Protocol server of the Conv2pdf API. Your AI assistant converts Word, Excel, PowerPoint, Pages, images, e-books, PostScript and HTML files to PDF, as well as web pages from their address, converts PDFs to Word or to images, and merges, splits, compresses, protects, rotates or numbers the PDFs that are on your computer. Processing runs on OVHcloud servers in France: no transfer outside the EU, no US service in the chain.
Installation · Tools · How it behaves · Development
Installation
Create an account on conv2pdf.com. The Dev plan includes 300 free conversions, valid for 12 months; see pricing for the paid plans.
Create an API key, which starts with
cpdf_live_, in the Developer tab of your dashboard. Conv2pdf shows it only once, at creation.Add the server to your MCP client, with the key in the
CONV2PDF_API_KEYenvironment variable. It needs Node.js 22 or later.
In Claude Code:
claude mcp add --env CONV2PDF_API_KEY=cpdf_live_... --transport stdio conv2pdf -- npx -y conv2pdf-mcpOn Windows, put cmd /c before npx.
In Claude Desktop, Cursor and the other clients configured with a JSON file:
{
"mcpServers": {
"conv2pdf": {
"command": "npx",
"args": ["-y", "conv2pdf-mcp"],
"env": { "CONV2PDF_API_KEY": "cpdf_live_..." }
}
}
}Or, in Claude Code, install the plugin: the same server, with a skill that tells the assistant which tool to call, in which order, and what a call costs.
/plugin marketplace add conv2pdf/mcp
/plugin install conv2pdf@conv2pdfClaude Code asks for the API key when the plugin is enabled, and keeps it in the credential store of the system, not in a settings file. To set it later, run /plugin configure conv2pdf@conv2pdf, or open /plugin, Installed tab, conv2pdf, Configure options. A server you added by hand with the npx -y conv2pdf-mcp command takes precedence over the one of the plugin.
For another agent that loads SKILL.md skills, add the server as above and take the skill alone: plugin/skills/conv2pdf/SKILL.md in this repository, also listed on Agensi.
Then ask for what you need: "convert report.docx to PDF", "merge these three PDFs", "compress scan.pdf and protect it with a password".
Related MCP server: 1pdf
Tools
Tool | What it does |
| Word, Excel, PowerPoint, OpenDocument, Apple Pages, RTF, TXT, CSV, PNG, JPG, WebP, GIF, TIFF, HEIC, EPUB, PostScript (PS, EPS) or HTML file to PDF, chosen from the extension |
| Public web page to PDF, from its address, printed as a browser would |
| iPhone HEIC or HEIF photo to JPG |
| PDF with real text to an editable DOCX document |
| One PNG or JPG per page, in a ZIP file |
| Combine several PDFs into one, in the order given |
| Copy the pages you list, such as |
| One PDF per page, in a ZIP file |
| Turn every page by 90, 180 or 270 degrees |
| Number the pages, as "3 / 12" or "3", bottom center, left or right |
| Stamp a text of up to 50 characters on every page |
| Reduce the size, keeping images at 72, 150 or 300 DPI |
| Set a password, and optionally forbid printing or copying |
| Remove a password you know, or the printing and copying restrictions |
| Plan, usage and limits of the API key |
How it behaves
Files stay on your computer, except for the conversion. A tool takes the path of a file, sends the file to Conv2pdf and writes the result on your disk. Conv2pdf checks the content of the file, not only its name.
Nothing is overwritten. The result goes next to the input file:
report.docxgivesreport.pdf, and a PDF tool adds a suffix, such asreport-compressed.pdf. When that name is taken, the server writesreport (2).pdf. The assistant can choose the place withoutput_path; if a file is already there, the tool refuses before converting anything. A web page has no input file to write next to, soconvert_url_to_pdfalways takes anoutput_path.Deleted from the server. Once the result is on your disk, the server deletes the job from Conv2pdf. Should that fail, Conv2pdf deletes the files after one hour.
Quota. Each conversion counts as one in the quota of your plan, including one that Conv2pdf refuses after reading the file, such as an unreadable or scanned PDF, or one with too many pages. A file refused on arrival (wrong type, too large, password missing), a refused setting (a page range that does not exist, a password that is too short) and a failure on the side of Conv2pdf count for nothing, and
get_quotais free. Files can weigh up to 10 MB on the Dev plan and 200 MB on paid plans.Rate limit. The API accepts 20 conversions per minute per API key. When it asks to slow down, or when its queue is full, the server waits for the delay the API gives and tries again, twice at most and only for delays of 30 seconds or less; otherwise the assistant gets the delay to wait.
Protected PDFs. The tools that read a PDF, except
merge_pdfs, open one that asks for a password when the assistant passes it aspassword. The result has no password. For a merge, unlock the protected PDFs first.Pages and Numbers. A Pages document keeps its
.pagesextension: only the name tells it from a Numbers spreadsheet, which Conv2pdf does not convert, like Keynote presentations.Errors. A refusal comes back to the assistant as a sentence it can act on: the wrong password, the page range that does not exist, the plan limit, the key to set. A cancelled call stops the transfer and leaves no file behind.
Without a key. The server starts and lists its tools; a call explains how to set
CONV2PDF_API_KEY.
Every request carries User-Agent: conv2pdf-mcp/<version>. Mention it when you contact support: it tells your calls apart in the API's logs.
Development
The server has no dependency: Node.js runs the sources as they are. It talks to its client over stdio and serves both eras of the protocol from the same process: revision 2026-07-28, where each request carries its protocol version, and the earlier revisions (2025-11-25 down to 2024-11-05), which start with an initialize handshake.
npm testruns the tests against a fake Conv2pdf API on a local port: no key and no network are needed.
The tools of the server and the extensions convert_to_pdf routes on follow what the live API publishes (GET /v1/tools): our monitoring compares them every day, and says when the API gains a tool or an extension that the server does not have.
Plugin
plugin/ holds the Claude Code plugin: its manifest, the .mcp.json that starts the published package with npx, and the skill, plugin/skills/conv2pdf/SKILL.md. .claude-plugin/marketplace.json is the catalog that lets Claude Code install the plugin from this repository. Neither is part of the npm package. npm test checks that the plugin is at the version of the package and that the skill names the tools the server has.
claude plugin validate . --strict
claude --plugin-dir ./plugincheck the manifests, then start a session with the plugin loaded from the folder, without installing it. A user gets a change of the plugin or of the skill when the version changes: it ships with a release.
Releasing
Set the version in
package.json,server.jsonandplugin/.claude-plugin/plugin.json, and date its section inCHANGELOG.md.Run
npm test.Commit, then push a tag named after the version: the Publish workflow publishes the package to npm through Trusted Publishing, with a provenance statement.
Publish the entry of the MCP Registry:
mcp-publisher login http --domain conv2pdf.com, thenmcp-publisher publish. The namecom.conv2pdf/conv2pdfis proved by the public key served athttps://conv2pdf.com/.well-known/mcp-registry-auth.When the skill changed, upload it again to its Agensi listing, as a new version: a ZIP of a
conv2pdf/folder that holds theSKILL.md. Nothing updates the listing from this repository.
Resources
Support
Open an issue or write to contact@conv2pdf.com.
License
MIT, see LICENSE.
Available Tools
13 toolsadd_page_numbersAdd Page Numbers to PDFA
Prints the page number at the bottom of every page of a PDF. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), format, password, position, +1 more.
add_watermarkAdd Watermark to PDFA
Stamps a text diagonally across every page of a PDF. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: text (required), input_path (required), password, output_path.
compress_pdfCompress PDFA
Reduces the size of a PDF by lowering the resolution of its images. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), quality, password, output_path.
convert_heic_to_jpgConvert HEIC to JPGA
Converts an iPhone HEIC or HEIF photo to a JPG image. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), output_path.
convert_pdf_to_imagesConvert PDF to ImagesA
Renders each page of a PDF as an image at 150 DPI. The result is one ZIP archive with an image per page. Up to 100 pages. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), format, password, output_path.
convert_pdf_to_wordConvert PDF to WordA
Converts a PDF that contains real text to an editable Word document (DOCX). A scanned PDF, made of images without text, is refused. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), password, output_path.
convert_to_pdfConvert to PDFA
Converts a document, an image or an e-book to PDF: Word, Excel, PowerPoint, OpenDocument, Apple Pages, RTF, TXT, CSV, PNG, JPG, WebP, GIF, TIFF, HEIC and EPUB. The converter is chosen from the extension of the file. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), output_path.
extract_pdf_pagesExtract Pages From PDFA
Keeps some pages of a PDF in a new PDF. The pages keep the order they have in the document. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: pages (required), input_path (required), password, output_path.
get_quotaGet QuotaARead-only
Returns the plan of the conv2pdf API key and how many conversions it has used and may still use. Reading the quota is free.
merge_pdfsMerge PDFsA
Combines several PDFs into one, in the order given. 2 files on the Dev plan, up to 20 on paid plans. The result is written next to the first file. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_paths (required), output_path.
protect_pdfProtect PDF With PasswordA
Encrypts a PDF (AES-256) so that it asks for a password to open, and optionally forbids printing or copying. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: password (required), input_path (required), output_path, prevent_copy, +1 more.
rotate_pdfRotate PDFA
Rotates every page of a PDF clockwise. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: rotation (required), input_path (required), password, output_path.
unlock_pdfUnlock PDFA
Removes the password and the restrictions of a PDF whose password is known. It does not find a forgotten password. The file is uploaded to conv2pdf and the call counts as one conversion.
Inputs: input_path (required), password, output_path.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool targets a clearly distinct operation: input-side conversions (convert_to_pdf, convert_heic_to_jpg), output-side conversions (convert_pdf_to_word, convert_pdf_to_images), and discrete PDF edits (merge, extract, rotate, watermark, compress, protect, unlock). The only superficially adjacent pair (convert_to_pdf handling HEIC/JPG vs convert_heic_to_jpg producing PNG/JPG) differs clearly in direction and output format.
All 13 tools use snake_case with a consistent verb-first convention (convert_*, merge_pdfs, extract_pdf_pages, rotate_pdf, add_*, compress_pdf, protect_pdf, unlock_pdf, get_quota). No camelCase or mixed-style outliers.
13 tools is well-scoped for a PDF conversion and manipulation service, with each tool mapping to a genuine, non-redundant operation. No filler or trivially duplicated tools.
Strong coverage of the core lifecycle: conversion both directions, merge, page extraction, rotation, annotation (watermark, numbering), compression, encryption and decryption, plus quota checking. Minor gaps remain (e.g. PDF to text/Excel, splitting into separate per-page files, page deletion/reordering), but the surface covers nearly all common workflows.
Related MCP Connectors
Convert files between 200+ formats and merge, compress, OCR, watermark or redact PDFs.
Convert PDFs/images to Word, Excel, and Markdown. Split, merge, and watermark PDF files.
Merge, split, extract, rotate, reorder and stamp PDF pages from your AI chat, all offline.
Merge, split, extract, rotate, reorder and stamp PDF pages from your AI chat, all offline.
Related MCP Servers
- AlicenseAqualityBmaintenanceA local-first PDF tool for merging, splitting, rotating, watermarking, Bates-numbering, cleaning metadata, and counting pages — all operations happen on your machine with no network transmission.1513 npm1MIT
- AlicenseCqualityDmaintenanceEnables AI assistants to perform PDF operations like merge, split, compress, convert, encrypt, OCR, and summarize using natural language.9815 npmMIT
- FlicenseBqualityBmaintenanceEnables local, offline document extraction and manipulation—PDF first but also HTML, DOCX, XLSX, PPTX, EML, EPUB, Markdown, and plain text—through tools for probing, locating, extracting, converting, assembling, OCR, protecting, and redacting documents, with nothing leaving the machine.7-
- AlicenseBqualityCmaintenanceEnables AI agents to convert documents, images, and data files across 50+ format pairs and to run PDF/image operations such as merge, split, compress, rotate, protect, unlock, extract text, and resize or compress images. Files are passed URL-in and returned URL-out (or saved locally in stdio mode), with tools for checking credits and generating Stripe checkout or billing-portal links.1850 PyPIMIT