pdfdocument-processingdeveloper-toolsmcp
Generates PDFs from HTML, URLs, or templates and extracts text or Markdown from PDFs through MCP.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
Not yet automatically verified
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.
Manual Client & Custom JSON ConfigExpand JSON ▾
Client Config & Setup
Choose your client or environment
Target File:
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Overview
Use cases
Generate invoices or reports from HTML and structured data
Convert public web pages into PDF documents
Extract Markdown or text from PDF files
Check scanned PDFs for OCR requirements
Key features
HTML, URL, and template-to-PDF generation
Chromium-based PDF rendering
PDF text and Markdown extraction
URL and base64 PDF inputs
Page count and OCR-needed reporting
Optional PDF page settings
Capabilities & Tool Schemas (2)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Docweave MCP.
generate_pdf`source` (one of: raw `html`, a public `url`, or a `template` + `data`) → a PDF.
read_pdf`source` (`url` or `base64`) → extracted `content` (markdown or text) + `pageCount`.
How Docweave MCP works
What docweave/mcp MCP server does
The docweave/mcp MCP server provides two document-focused tools through the Model Context Protocol: generate_pdf and read_pdf. It is the MCP package for Docweave and is intended for clients such as Claude Desktop, Cursor, and Windsurf.
generate_pdf creates a PDF from one of three inputs: raw HTML, a public URL, or a template together with JSON data. Page settings can optionally specify the paper format, landscape mode, and margins. Rendering uses Chromium, so the tool is suited to producing PDFs from web-oriented document content.
read_pdf accepts a PDF URL or base64-encoded PDF data. It returns extracted content as text or Markdown, along with the document's page count. For scanned or image-only PDFs, the response reports needsOcr: true rather than returning empty extracted text.
How it works
An MCP client invokes either tool and supplies a structured source value. For PDF generation, the source identifies HTML, a public URL, or a template and its associated data. For PDF reading, the source identifies a URL or base64 content. The generated document or extracted result is returned to the client through MCP.
URL-based rendering is restricted by SSRF protections, and generation supports idempotency keys. The hosted service is available at https://docweave.dev/api/mcp. Requests sent to that hosted API require a Docweave bearer API key.
Setup and configuration
The docweave/mcp MCP server can run locally from the published npm package with:
A Claude Desktop configuration can register it as a local stdio server using npx and the -y flag. The package includes its render engine, so the documented installation does not require a separate Chromium setup.
Alternatively, an MCP client can use the hosted streamable-HTTP endpoint without installing the package. Hosted calls authenticate with a Docweave API key in the Authorization: Bearer ... header. The README states that a free account includes 50 documents per month without a card; usage is priced per document rather than per page.
Tools and capabilities
- Generate PDFs from raw HTML.
- Render a public URL as a PDF.
- Populate a template with JSON data before PDF generation.
- Set PDF format, orientation, and margins.
- Read PDFs from URLs or base64 input.
- Return extracted text or Markdown and a page count.
- Flag scanned documents that need OCR.
Limitations and notes
The URL input for generation must be public, and URL rendering includes SSRF protections. The documented reading behavior identifies scanned PDFs with needsOcr; it does not state that OCR is performed by the server. Hosted use requires a Docweave API key, while the README does not specify a separate credential requirement for the local command. Pricing information in the source applies to Docweave document processing, not to the open-source package itself.
The docweave/mcp MCP server is licensed under MIT. Its repository is the source for the @docweave/mcp npm package, and the package is also listed in the official MCP registry.
Related MCP Servers
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
npm downloads
437
Package downloads in the last 30 days.
Last commit
1mo ago
Most recent push to the default branch.
Tools exposed
2
Callable tools this server registers over MCP.
Directory activity
3 views
Config copies, upvotes, and views on AllMCPs.
Reviews
No reviews yet — be the first to share how this listing worked for you.
Frequently Asked Questions about Docweave MCP
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/docweave-mcp)HTML Embed
<a href="https://allmcps.com/mcp/docweave-mcp"><img src="https://allmcps.com/api/badge/docweave-mcp?style=directory" alt="Docweave MCP on AllMCPs" /></a>