PDF4me MCP server
12 operations0 webhooks
PDF4me is a PDF and document processing SaaS. This plugin merges, splits, compresses and organizes PDFs, converts them to Word and renders HTML to PDF, runs OCR, reads PDF metadata, extracts tables and form data, and polls asynchronous processing jobs. File answers come back base64-encoded.
Try PDF4me with your agent
Connect PDF4me, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in PDF4me on my account, then run one read-only example and show me the result.
PDF4me tools and triggers
Tools are what your agent can do in PDF4me through Corsair's MCP server. Triggers are the PDF4me events a routine can start from.
- CompressDestructive
Compress a PDF with a documented profile (Max, Web, Print, Default)
pdf.compress
- Delete PagesDestructive
Return a copy of a PDF without the given pages; the source file is not changed
pdf.deletePages
- Extract PagesDestructive
Extract the given pages into a new PDF
pdf.extractPages
- Get InfoRead-only
Read PDF metadata: page count, dimensions, author and more
pdf.getInfo
- MergeDestructive
Merge multiple PDFs into one; array order is the merge order
pdf.merge
- SplitDestructive
Split a PDF after a page, every N pages, after listed pages or by page ranges; the parts come back in documents
pdf.split
Convert
- Html To PdfDestructive
Render HTML content into a PDF
convert.htmlToPdf
- Ocr PdfDestructive
Run OCR on a scanned PDF to make its text editable; the API answers a job, so poll jobs.status for the file
convert.ocrPdf
- Pdf To WordDestructive
Convert a PDF to a Word document; the API answers a job, so poll jobs.status for the file
convert.pdfToWord
Extract
- Pdf Form DataRead-only
Extract the values of filled PDF form fields
extract.pdfFormData
- Table From PdfRead-only
Extract tables from a PDF
extract.tableFromPdf
Jobs
- StatusRead-only
Poll a job (isAsync, or PDF-to-Word and OCR, which always run as jobs); a finished job answers its file
jobs.status
Connect PDF4me to Claude, ChatGPT or Cursor
- 1
Connect PDF4me in Corsair
Add your PDF4me API key once in Corsair. Corsair stores the credential encrypted and makes the PDF4me API calls for your agent, so it never goes into a prompt or a config file. Connect PDF4me
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs PDF4me. On a ChatGPT personal plan, connect PDF4me here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, PDF4me's read and write operations run right away and its 8 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/pdf4me, add the PDF4me plugin, and connect with an API key. Then call methods like corsair.pdf4me.api.convert.htmlToPdf() from your app. Corsair keeps each tenant isolated.
Yes. PDF4me requires an API key from your PDF4me account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit PDF4me, GitHub, Notion, Stripe, and the rest. Trigger PDF4me from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for PDF4me is a PDF and document processing SaaS. This plugin merges, splits, compresses and organizes PDFs, converts them to Word and renders HTML to PDF, runs OCR, reads PDF metadata, extracts tables and form data, and polls asynchronous processing jobs. File answers come back base64-encoded. Common builds include sync jobs, admin tooling, and agents that call PDF4me APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per PDF4me API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/pdf4me in the open repo. When PDF4me ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your PDF4me data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store PDF4me data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put PDF4me on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 8 destructive PDF4me operations. You can change a link's mode at hub.corsair.dev/me.