Click on "Install 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., "@@docweave/mcp generate a PDF from this URL: https://example.com/report"
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.
The open-source MCP server for Docweave — give any MCP client (Claude, Cursor, Windsurf, and others) two document tools:
generate_pdf — turn raw HTML, a public URL, or a template + JSON into a real PDF.
read_pdf — turn a PDF (URL or base64) into clean text / markdown, with a needsOcr
flag for scanned documents.
One MCP server for an agent's document I/O — write a document, read a document — priced per document, not per page.
npx @docweave/mcpOr use the zero-install hosted endpoint: https://docweave.dev/api/mcp.
{
"mcpServers": {
"docweave": { "command": "npx", "args": ["-y", "@docweave/mcp"] }
}
}Tool calls that hit the hosted API authenticate with a Docweave API key
(Authorization: Bearer dw_live_…) — get one free at https://docweave.dev/signup
(50 documents/month, no card).
Related MCP server: pdf-navigator-mcp
generate_pdfsource (one of: raw html, a public url, or a template + data) → a PDF.
Optional page options (format, landscape, margins). Idempotency-key aware, SSRF-guarded
URL rendering.
read_pdfsource (url or base64) → extracted content (markdown or text) + pageCount.
Scanned/image PDFs return needsOcr: true instead of empty text.
This is the source of the @docweave/mcp
npm package, published from the Docweave monorepo and listed on the
official MCP registry as
io.github.NicolasMartalog/docweave-mcp. The npm package ships bundled with its render
engine; install it with npx as above.
MIT
Generate a PDF from raw HTML, a public URL, or a template + JSON data. Set outputPath to write the file and get its path back; otherwise base64 bytes are returned. The canonical way for an AI agent to turn content into a shareable, correctly-formatted PDF.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | What to render. Provide exactly one of: html, url, or (template|templateId) with data. | |
| options | No | Optional page and print settings. | |
| outputPath | No | Absolute path to write the PDF to. If omitted, base64 is returned. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate the tool is idempotent and non-destructive. The description adds context about file writing and base64 return but does not disclose potential side effects like network requests or private address blocking (though blocking is mentioned in schema). No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. The first sentence states the core function and source types; the second explains output behavior. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (3 params, nested objects, no output schema) and 100% schema coverage, the description covers the essential decision points (source types, output behavior) without redundancy. It is complete for proper usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all parameters have descriptions. The description adds value by clarifying the outputPath behavior (returns path vs base64) which is not fully captured in schema. Options are not described in description but are well-documented in schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it generates a PDF from three specific sources (HTML, URL, template), with a strong verb-resource pair. No sibling tools exist, so differentiation is not required.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly mentions it as the canonical way for an AI agent to create a PDF, and explains the two behaviors (file vs base64). However, it does not include when-not-to-use scenarios or alternatives, but given no siblings, this is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity or confusion between tools. The single tool has a clear, distinct purpose.
The tool name 'generate_pdf' follows a clear verb_noun pattern. With only one tool, consistency is perfect and the name is descriptive.
A single tool suggests a very narrow scope. While PDF generation is a specific task, the server might benefit from additional related tools (e.g., listing templates or managing output) to feel more complete. The count is borderline thin.
The tool covers multiple input types (HTML, URL, template+data) and options (file path or bytes). However, there is no management of templates or output files, and no other lifecycle operations, leaving notable gaps for a full document workflow.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for the PDFGate API. Generate PDFs, manage documents and handle e-signatures.
HTML-to-PDF MCP server — render pixel-faithful PDFs from HTML.
MCP server for Api2Pdf — generate PDFs & images from HTML, URLs or office files; merge, barcodes.
Generate PDF, Word (.docx) and PowerPoint (.pptx) documents from Markdown over MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/NicolasMartalog/docweave-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
