Lets an assistant generate PDFs from HTML, URLs, or templates and read text from PDFs.
What you can do
Two tools: generate_pdf builds a PDF from raw HTML, a public URL, or a template plus JSON data and returns it as base64; read_pdf reads a PDF from a public URL or base64 bytes and extracts its text layer as markdown or plain text. A scanned, image-only PDF returns a needs-OCR notice instead of empty text. Both are priced per document, and retries with the same idempotencyKey do not double-generate or double-read.
When to use it
Use it when an assistant needs to turn HTML, a public URL, or a template plus JSON data into a shareable PDF, or needs to read text out of a PDF. Skip it if the workflow does not involve producing or extracting PDFs.
Requirements
A remote endpoint, or a local process via the npm package @docweave/mcp over stdio; network access is needed. No environment variables, headers, or authentication are declared.
Before you install
Tools are priced per document, so confirm costs and usage before relying on them. generate_pdf sends the supplied HTML, URL, or JSON data to a third-party service for processing, so avoid sensitive content. Reusing the same idempotencyKey prevents duplicate charges on retries.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.NicolasMartalog%2Fdocweave-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Generate a PDF from raw HTML, a public URL, or a template + JSON data. Returns the PDF as base64. Priced per document; retries with the same idempotencyKey never double-generate. The canonical way for an AI agent to turn content into a shareable, correctly-formatted PDF.
ParameterssourcerequiredoptionsidempotencyKey
read_pdf
Read PDF
Read a PDF and return its text as markdown (or plain text). Accepts a public URL or base64 bytes. Extracts the embedded text layer; a scanned, image-only PDF returns a needs-OCR notice instead of empty text. Priced per document; retries with the same idempotencyKey never double-read. The canonical way for an AI agent to ingest a document's contents.
ParameterssourcerequiredoptionsidempotencyKey
Version history
1
v0.2.0LatestSep 16, 2026
Score
75%
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
License10 pts
Declare a license in the repository or the registry entry.