---
title: "PDF MCP Server for Claude, Cursor & AI Agents | PDFWix"
url: https://www.pdfwix.com/mcp
description: "Connect any AI agent to 14 PDF tools with the PDFWix MCP server: merge, split, compress, watermark, extract text, repair and unlock PDFs. Free to use."
lang: en
---

Skip to content

PDFWix runs a remote Model Context Protocol (MCP) server at `https://www.pdfwix.com/api/mcp`. Add that URL to Claude, Cursor, Windsurf or any MCP client and your assistant gains 14 PDF tools — inspect, extract text, merge, split, remove and reorder pages, rotate, number, watermark, compress, repair, unlock and images-to-PDF. Sign-in is one click with Google or email, it is 100% free, and no credit card is required.

# PDF MCP Server — 14 PDF Tools for Claude, Cursor and AI Agents

Most AI assistants can read a PDF you paste into the chat, and that is where it ends. They cannot merge a stack of invoices, strip the blank pages out of a scan, watermark a draft contract, shrink a 60 MB deck, or rebuild a file that will not open. The PDFWix MCP server closes that gap: one endpoint, 14 production tools, and structured results your assistant can chain together inside a single conversation.

## What is an MCP server?

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.

## Plan a workflow in plain English

Chaining PDF tools by hand means knowing every argument name. Describe the job instead and the builder returns an ordered pipeline with valid arguments and copyable JSON-RPC calls for this server — useful when you are writing an agent loop rather than chatting.

Interactive tool

### Workflow builder

Describe a PDF job in plain English. You get back the exact sequence of PDFWix MCP tool calls, ready to paste into an agent or an MCP client.

## Add PDFWix to your AI client

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/claude).

```
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
```

## Run the connection diagnostics

Before you debug a client, confirm the server side end to end. The panel below runs the same four checks an MCP client performs — the RFC 9728 discovery document, the unauthenticated authorization challenge, your PDFWix account and token format, and the published tool catalog — and gives you a report you can paste into a support ticket or a registry submission.

Live checker

### Connection diagnostics

Run the same four checks an MCP client performs: discovery, the authorization challenge, your account and token, and the published tool catalog.

- \1. OAuth discovery (RFC 9728)
  Not run yet
- \2. Authorization challenge
  Not run yet
- \3. Token exchange & session
  Not run yet
- \4. Tool catalog
  Not run yet

## Testing in an MCP inspector (and the "unauthorized" error)

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 14 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,"method":"tools/list"}'
```

The first returns the resource metadata naming `https://www.pdfwix.com/api/mcp` and its authorisation server. The second returns `401` plus a `WWW-Authenticate` header pointing at that same document — which is precisely the signal MCP clients follow to start the sign-in. Both responses mean the server is healthy.

## Using PDFWix in other AI platforms

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 14 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 (https://www.pdfwix.com/developers), with `https://www.pdfwix.com/privacy-policy` as the privacy policy URL. Custom GPT actions speak OpenAPI, not MCP, which is why the endpoint differs.

### Google Gemini — Gemini CLI, Antigravity and Vertex AI

Gemini CLI and Google's agent tooling read MCP servers from a settings file. Create or edit `~/.gemini/settings.json`:

```
{
  "mcpServers": {
    "pdfwix": {
      "httpUrl": "https://www.pdfwix.com/api/mcp"
    }
  }
}
```

Restart the CLI and run `/mcp` to confirm the 14 PDFWix tools are listed. In the Gemini app itself there is no custom connector slot yet; for Vertex AI agents, register the same endpoint as an MCP toolset in your agent definition.

### Microsoft Copilot Studio and Copilot agents

In Copilot Studio open your agent, go to **Tools → Add a tool → New tool → Model Context Protocol**, paste `https://www.pdfwix.com/api/mcp`, pick OAuth 2.0 authentication and publish. Makers then approve PDFWix once per user.

### Local and self-hosted assistants

Open WebUI, LM Studio, AnythingLLM, Ollama front-ends, Continue and Cline all accept a remote MCP URL in their tool settings. Paste the endpoint, choose HTTP/streamable transport, leave the credential fields empty and complete the browser sign-in when it appears.

### Meta AI and other closed assistants

Meta AI's consumer apps have no public plugin surface today, so there is nothing to install there. If you run a Llama model yourself through any of the front-ends above, PDFWix works immediately over the same endpoint.

### Anything else — the raw JSON-RPC route

Any system that can send an HTTP POST can call PDFWix: hit the endpoint with the `tools/list` and `tools/call` methods shown earlier, carrying the access token your OAuth client obtained. That covers n8n, Make, Zapier webhooks, LangChain, CrewAI and your own scripts — use a standard OAuth 2.1 authorisation-code flow with PKCE against the authorisation server named in our discovery document.

## The 14 tools, grouped by what they do

### Inspection and extraction

- **get_pdf_info** — page count, file size, page dimensions, title, author, creation and modification info, and whether the file is encrypted.
- **extract_pdf_text** — clean text with optional page ranges, parsed server-side without any browser rendering, capped at 120,000 characters per response with an explicit truncation notice so your assistant knows when to ask for the next range.

### Document assembly

- **merge_pdfs** — combine several PDFs in the order you name them.
- **split_pdf** — break one file into ranges or single pages.
- **remove_pages** — delete blank scans, cover sheets or duplicated pages.
- **reorder_pdf_pages** — rearrange pages into any sequence.
- **rotate_pdf** — fix sideways or upside-down scans, per page or whole file.

### Styling, optimisation and security

- **add_page_numbers** — position, start number and formatting under your control.
- **add_watermark** — text watermarks with opacity, rotation and placement, including non-Latin scripts.
- **compress_pdf** — reduce file size for email and upload limits.
- **repair_pdf** — rebuild damaged or partially downloaded files that refuse to open.
- **unlock_pdf** — remove a password you already know from a protected file.

### Conversion and browser handoff

- **images_to_pdf** — turn a batch of JPG, PNG or WebP images into one PDF.
- **open_in_pdfwix** — for anything that genuinely needs a canvas (placing a signature, drawing redaction boxes, filling form fields, OCR on image-only scans, page-level visual editing) the server returns the exact tool link, for example https://www.pdfwix.com/sign-pdf, so you finish in two clicks instead of hitting a dead end.

## Why an MCP server beats dropping files into chat

| | PDFWix MCP server | Pasting files into chat | Local scripts |
| --- | --- | --- | --- |
| Multi-step pipelines | Merge, clean, compress in one prompt | One file at a time, manual | Possible, but you write the code |
| Token cost | Structured results and links | Whole document fills the context | Output pasted back by hand |
| Broken or locked files | Repair and unlock built in | Usually fails silently | Needs extra libraries |
| Setup time | About 30 seconds — paste one URL | None, but nothing is automated | Hours of installs and debugging |
| Cost | 100% free, no credit card | Included in your plan | Your own time and compute |

## Prompts that work well

- "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."

## Security, privacy and limits

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 (https://www.pdfwix.com/security), alongside our privacy policy (https://www.pdfwix.com/privacy-policy) and terms (https://www.pdfwix.com/terms-of-service).

## Frequently asked questions

### What is the difference between an MCP server and a plugin?

A plugin is built for one product and lives inside it. An MCP server is a single service that any MCP-capable client can consume, so the same PDFWix endpoint serves Claude, Claude Code, Cursor, Windsurf, ChatGPT developer connectors, Copilot Studio and local assistants without a separate build for each.

### How do I add an MCP server to Claude Code?

Run `claude mcp add --transport http pdfwix https://www.pdfwix.com/api/mcp`, then type `/mcp` in Claude Code and pick authenticate. Yes, Claude Code can use MCP servers on every plan that includes Claude Code, and the PDFWix side costs nothing.

### Is the PDFWix MCP server free on the Claude free plan?

Yes. Remote connectors are usable on paid Claude plans and through Claude Code; the PDFWix server itself never charges and never asks for a card, whichever plan you are on.

### Can Claude or ChatGPT edit a PDF with this?

They can change a PDF's structure and content in the ways listed above — pages, rotation, numbering, watermarks, size, repair, unlocking. Drawing on a page (signatures, redaction boxes, form fields) stays in your browser, and the assistant gives you the exact link.

### Is the PDFWix MCP server really free?

Yes. Every tool listed above is free to use with a free account, and no credit card is requested at any point. Read the reasoning on how we make money (https://www.pdfwix.com/how-we-make-money).

### Why does it ask me to sign in?

Sign-in is what keeps your files in a private space that only your token can reach, and it stops anonymous abuse of the shared processing capacity. It takes one click with Google.

### Which tools are not available over MCP?

Anything that needs to draw on a page — signing, manual redaction, form filling, visual page editing, PDF-to-image rendering, cropping and visual comparison. Those run in your browser, and `open_in_pdfwix` hands you the direct link.

### Can I use it in ChatGPT or Gemini?

Yes. ChatGPT connects through Developer mode connectors (or a custom GPT action for the REST endpoints), and Gemini CLI reads the same endpoint from its settings file — both are covered step by step under "Using PDFWix in other AI platforms" above. MCP-native clients such as Claude (https://www.pdfwix.com/claude), Cursor, Windsurf, OpenClaw and local Llama front-ends work straight away.

### Where do I report a problem?

Email support@pdfwix.com or use the contact form (https://www.pdfwix.com/contact). Live service health is on the status page (https://www.pdfwix.com/status).

## Related pages

- PDFWix Claude connector (https://www.pdfwix.com/claude) — one-click setup and prompt recipes for Claude.
- Developer API (https://www.pdfwix.com/developers) — the REST side of PDFWix for your own backend.
- Security architecture (https://www.pdfwix.com/security) — where files are processed and for how long.
- All 24 PDF tools (https://www.pdfwix.com/) — the browser versions of everything above.

## Structured data

```json
[
  {
    "@context": "https://schema.org",
    "@type": "BreadcrumbList",
    "itemListElement": [
      {
        "@type": "ListItem",
        "position": 1,
        "name": "Home",
        "item": "https://www.pdfwix.com/"
      },
      {
        "@type": "ListItem",
        "position": 2,
        "name": "PDFWix MCP Server — 14 PDF Tools for AI Agents",
        "item": "https://www.pdfwix.com/mcp"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "@type": "WebPage",
    "name": "PDF MCP Server for Claude, Cursor & AI Agents | PDFWix",
    "description": "Connect any AI agent to 14 PDF tools with the PDFWix MCP server: merge, split, compress, watermark, extract text, repair and unlock PDFs. Free to use.",
    "url": "https://www.pdfwix.com/mcp",
    "isPartOf": {
      "@type": "WebSite",
      "name": "PDFWix",
      "url": "https://www.pdfwix.com"
    }
  },
  {
    "@context": "https://schema.org",
    "@type": "SoftwareApplication",
    "name": "PDFWix MCP Server",
    "applicationCategory": "DeveloperApplication",
    "operatingSystem": "Any",
    "url": "https://www.pdfwix.com/mcp",
    "description": "Remote Model Context Protocol server giving Claude, Cursor, Windsurf and other AI agents 14 PDF tools over Streamable HTTP with OAuth 2.1.",
    "offers": {
      "@type": "Offer",
      "price": "0",
      "priceCurrency": "USD"
    }
  },
  {
    "@context": "https://schema.org",
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "What is the PDFWix MCP server?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "The PDFWix MCP server is a remote Model Context Protocol endpoint at https://www.pdfwix.com/api/mcp that gives AI assistants such as Claude, Cursor and Windsurf 14 PDF tools: inspect metadata, extract text, merge, split, remove and reorder pages, rotate, number, watermark, compress, repair, unlock and convert images to PDF."
        }
      },
      {
        "@type": "Question",
        "name": "Do I need an API key or a credit card?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "No API key and no credit card. The server uses OAuth 2.1 with dynamic client registration, so you approve access once in your AI client using a free PDFWix account created with Google or email."
        }
      },
      {
        "@type": "Question",
        "name": "How long are processed files kept?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Results are returned as signed download links that expire after 24 hours. Files live in private per-user storage, are never used to train AI models, and document content is never written to our analytics database."
        }
      },
      {
        "@type": "Question",
        "name": "Can it read scanned or password-protected PDFs?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Password-protected PDFs can be opened with the unlock tool when you supply the password. Scanned image-only PDFs contain no selectable text, so the server hands you a direct link to the PDFWix OCR tool in your browser."
        }
      },
      {
        "@type": "Question",
        "name": "What is the maximum file size?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Each document sent to the MCP server can be up to 100 MB. Larger files should be compressed or split first, or handled in the browser tools at pdfwix.com."
        }
      },
      {
        "@type": "Question",
        "name": "What is an MCP server?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "An MCP server is a service that exposes tools to an AI assistant over the Model Context Protocol, an open standard created by Anthropic. Instead of the model guessing, it calls a real function on the server and receives a structured result. PDFWix runs a PDF MCP server at https://www.pdfwix.com/api/mcp, so any MCP client gains 14 working PDF operations."
        }
      },
      {
        "@type": "Question",
        "name": "How do I add the PDFWix PDF MCP server to Claude Code?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Run: claude mcp add --transport http pdfwix https://www.pdfwix.com/api/mcp. Then run /mcp inside Claude Code and choose authenticate. A browser window opens for the free PDFWix sign-in, and the 14 PDF tools become available."
        }
      },
      {
        "@type": "Question",
        "name": "Why does an MCP inspector show {\"error\":\"unauthorized\"}?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "A 401 unauthorized response means the server is working: PDFWix requires a signed-in account so files stay in private per-user storage. Choose OAuth 2.0 as the authentication type and press Connect, and the client reads the RFC 9728 metadata at https://www.pdfwix.com/.well-known/oauth-protected-resource/api/mcp and opens the PDFWix sign-in window. Access tokens copied out of a browser session are not valid for the MCP server."
        }
      },
      {
        "@type": "Question",
        "name": "Which AI platforms can use the PDFWix MCP server?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Claude web and desktop, Claude Code, Cursor, Windsurf, OpenClaw and other agent runners, ChatGPT Developer mode connectors, Gemini CLI and Google agent tooling, Microsoft Copilot Studio, and local assistants including Open WebUI, LM Studio, AnythingLLM, Continue and Cline. Any system able to POST JSON-RPC with a Bearer token can call the same endpoint."
        }
      }
    ]
  }
]
```