Connect Claude, Cursor, Windsurf and other MCP clients to 14 PDF tools over one endpoint.
Connect Claude, Cursor, Windsurf and other MCP clients to 14 PDF tools over one endpoint.
An MCP server is a service that hands an AI assistant a set of real tools over the Model Context Protocol — the open standard Anthropic published in late 2024 and now supported by Claude, Cursor, Windsurf, ChatGPT developer connectors, Gemini CLI, Copilot Studio and most agent runners. The model no longer guesses at an answer: it calls a named function with typed arguments and gets a structured result back, exactly like a developer calling an API. A PDF MCP server applies that to documents. PDFWix exposes 14 PDF operations — metadata inspection, text extraction, merge, split, page removal, reordering, rotation, page numbering, watermarking, compression, repair, unlocking, images-to-PDF and a browser handoff — over a single HTTPS endpoint with OAuth sign-in. One paste of a URL, and your assistant can actually finish document work instead of describing it. SERVER ENDPOINT https://www.pdfwix.com/api/mcp Transport: Streamable HTTP (with SSE). Auth: OAuth 2.1 with dynamic client registration and RFC 9728 resource discovery. Protocol revision: 2025-06-18.
Every major MCP client accepts a remote server URL. Pick your client below. The first tool call opens a browser window where you approve access with a free PDFWix account — after that the connection stays live. Claude (web and desktop, remote connector): In Claude, open Settings → Connectors → Add custom connector, paste the URL below and approve the sign-in prompt. If you prefer the one-click route, use the public listing on the PDFWix Claude connector page. https://www.pdfwix.com/api/mcp Claude Desktop config file: { "mcpServers": { "pdfwix": { "url": "https://www.pdfwix.com/api/mcp" } } } Cursor (.cursor/mcp.json): { "mcpServers": { "pdfwix": { "url": "https://www.pdfwix.com/api/mcp", "transport": "http" } } } Windsurf, Open WebUI, LM Studio, AnythingLLM: All of these speak MCP natively. Add a remote/HTTP server, paste https://www.pdfwix.com/api/mcp, leave every credential field empty — there is nothing to copy, because authorisation happens in the browser rather than through a pasted key. Claude Code (command line): One command registers the server, then /mcp starts the sign-in: claude mcp add --transport http pdfwix https://www.pdfwix.com/api/mcp # then, inside Claude Code: /mcp → select pdfwix → Authenticate
If you open the endpoint in the Glama MCP Inspector, the official MCP Inspector, Postman or curl with no credentials and press Connect, you will see {"error":"unauthorized"} with HTTP 401. That is the server working correctly: PDFWix requires an account so your files land in private storage nobody else can reach. The fix: choose OAuth 2.0, not a pasted token: In the inspector's authentication settings pick OAuth 2.0 (leave client ID and secret empty — the server registers the client for you) and press Connect. The inspector reads our discovery document, opens the PDFWix sign-in window, and the status turns green with all 17 tools listed under the Tools tab. An access token copied out of a browser session will not work here, and no manual token is needed. The MCP endpoint only accepts tokens issued through the OAuth flow, which is what keeps one account's documents unreachable from another's. Verify the server is live from your terminal: These two calls confirm the endpoint and its discovery metadata without any credentials: # 1. discovery document (expect 200 with JSON) curl -s https://www.pdfwix.com/.well-known/oauth-protected-resource/api/mcp # 2. the endpoint itself (expect 401 + a WWW-Authenticate header) curl -i -X POST https://www.pdfwix.com/api/mcp \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"meth
MCP is becoming the shared standard, but each platform is at a different stage. Here is exactly where PDFWix plugs in today and what to do on platforms that speak a different protocol. OpenClaw and other autonomous agent runners: OpenClaw, OpenHands, AutoGPT-style runners and Claude Code all read a JSON server list. Add PDFWix as a remote HTTP server and approve the browser sign-in the first time a tool runs; the runner stores the authorisation and refreshes it on its own afterwards. { "mcpServers": { "pdfwix": { "type": "http", "url": "https://www.pdfwix.com/api/mcp" } } } For a fully headless machine, run the first authorisation once on a desktop with the same config directory, then copy the stored credentials across — the runner needs a browser only for that initial approval. ChatGPT — Developer mode connector or a custom GPT action: ChatGPT now supports remote MCP servers directly. In ChatGPT, open Settings → Connectors → Advanced → Developer mode, choose Create, paste https://www.pdfwix.com/api/mcp, set authentication to OAuth and approve the PDFWix sign-in. The 17 tools then appear in chat, and in Deep Research and agent runs. If your plan does not expose developer mode, build a custom GPT instead: Explore GPTs → Create → Configure → Create new action, and point the action at the PDFWix REST endpoints documented on the developer page, with https://www.pdfwix.com/privacy-p
INSPECTION AND EXTRACTION Page count, file size, page dimensions, title, author, creation and modification info, and whether the file is encrypted. Clean text with optional page ranges, parsed server-side without any browser rendering, capped at 120,000 characters with an explicit truncation notice. DOCUMENT ASSEMBLY Combine several PDFs in the order you name them. Break one file into ranges or single pages. Delete blank scans, cover sheets or duplicated pages. Rearrange pages into any sequence. Fix sideways or upside-down scans, per page or whole file. STYLING, OPTIMISATION AND SECURITY Position, start number and formatting under your control. Text watermarks with opacity, rotation and placement, including non-Latin scripts. Reduce file size for email and upload limits. Rebuild damaged or partially downloaded files that refuse to open. Remove a password you already know from a protected file. CONVERSION AND BROWSER HANDOFF Turn a batch of JPG, PNG or WebP images into one PDF. For anything that needs a canvas — placing a signature, drawing redaction boxes, filling form fields, OCR on image-only scans — the server returns the exact tool link, for example pdfwix.com/sign-pdf. Newly added: flatten_pdf locks filled form fields, signatures and comments into the page so nothing can be changed afterwards. edit_pdf_metadata sets or clears title, author, subject, keywords and creator…
Every tool takes a file as either an https url or inline base64. The url is the reliable path and it is what you should use almost every time. An assistant cannot stream binary data: to send base64 it has to type every byte out as text inside one reply, and model replies are capped at a few thousand tokens. Anything beyond roughly 20 KB gets clipped part way through, and the file that reaches the parser is genuinely broken, with a missing cross-reference table or a JPEG with no end marker. PDFWix now catches that before parsing. Input bytes are checked against the real file signature for PDF, JPG, PNG, WebP, GIF, TIFF, BMP and HEIC, unpadded or line-wrapped base64 is repaired automatically, and a payload that stops before its end marker comes back with a clear instruction instead of a parser stack trace: send a link, or open the browser tool. PDFs with junk before the header or a stale cross-reference table are re-read from the real header, so many files that used to fail now simply work. When chaining tools, pass the downloadUrl from one call straight into the next call url field, so no bytes ever travel through the conversation. For a file on someone computer, a Google Drive, Dropbox or OneDrive share link works as long as it resolves to the file itself rather than a preview page. For large or private files, ask for open_in_pdfwix: it returns the exact tool link and the…
"Using PDFWix, inspect this PDF and tell me the page count, dimensions and whether it is encrypted." "Extract the text from pages 4 to 9 with PDFWix and summarise the payment terms." "Merge these three invoices with PDFWix, drop the blank last page, then compress the result." "Watermark this contract with DRAFT at 30% opacity using PDFWix." "This PDF will not open — repair it with PDFWix and confirm the page count." "I need to sign this file myself. Give me the PDFWix link for that."
Authorisation uses OAuth 2.1 with dynamic client registration and per-user, token-scoped access, discovered over RFC 9728 from our own origin. Documents you send arrive as an HTTPS URL or a base64 payload, are processed in isolated server functions, and land in private per-user storage that nobody else can list or read. Download links are signed and expire after 24 hours. We never train AI models on your documents and never store document content in our database — only operational metrics such as which tool ran, whether it succeeded and how long it took. There is no sponsored or promoted content in any tool response, no payment handling, and no AI-generated media. Each document is capped at 100 MB; beyond that, compress or split first. Full detail lives on the security page, alongside our privacy policy and terms.
Yes. Every PDFWix tool is 100% free, with no credit card and no watermarks on your output.
Yes. Most PDFWix tools run entirely in your browser, so your file never leaves your device. Server-side tools use HTTPS and process files in memory only — we never store, sell, or train AI on your documents.
No account is required for any PDF tool. Sign-in is optional and only used for premium features like history sync.
No. PDFWix never adds watermarks to your output, even on the free tier.
Most browser-based tools handle PDFs up to 200 MB. Server-side tools like OCR support up to 100 MB per file.
Yes. Every tool is fully responsive and works in any modern browser on Windows, Mac, Linux, iPhone, iPad, Android and Chromebook.