Content Tools
paperbackkit.com
Provides tools for formatting, validating, and fixing print book manuscripts and EPUBs for Amazon KDP readiness and accessibility compliance.
ENDPOINT 1
https://paperbackkit.com/api/mcp
MCP server metadata
- Name
- paperbackkit
- Version
- 1.0.0
PaperbackKit prepares books for publishing. Word/KDP: check_kdp_readiness audits a .docx, format_manuscript_preview typesets it (free preview), calculate_book_spine gives spine/cover dimensions. EPUB accessibility (EU Accessibility Act): check_epub_accessibility runs the free automated audit, fix_epub_accessibility repairs the file for existing Fix My EPUB customers (license key required). Accessibility audits (Section 508 / WCAG / PDF-UA, all free): check_pdf_accessibility for PDFs, check_docx_accessibility for Word documents. KDP print troubleshooting: check_kdp_interior_pdf preflights an interior PDF for the usual rejection causes (unembedded fonts, wrong trim size). Ebook to print: format_epub_for_print typesets a reflowable .epub into a 6x9 KDP paperback interior (free preview). Covers: check_kdp_cover_pdf preflights a full-wrap cover PDF against the exact canvas KDP expects for the book. Large print: format_large_print_edition typesets a 7x10 16pt edition for low-vision readers. Wide distribution: check_ingramspark_interior_pdf preflights against IngramSpark's stricter PDF/X-1a requirements.
Known tools 12
calculate_book_spineCalculates the spine width and full paperback cover dimensions (with bleed) for an Amazon KDP print book, from page count, paper type, and trim size.
Inferred read-onlycheck_kdp_readinessRuns automated Amazon KDP formatting checks on a .docx book manuscript: chapter headings, first-line indents, spacing, margins/trim, table of contents, image alt text, and estimated page count.
Inferred read-onlyformat_manuscript_previewTypesets a .docx book manuscript into a print-ready 6x9 paperback interior (KDP-compliant mirrored margins, real chapter openers, table of contents) and returns the free preview: detected title/author/chapters, final page count, and images of the first pages.
Inferred read-onlycheck_epub_accessibilityRuns automated accessibility checks on an .epub ebook against the machine-checkable subset of EPUB Accessibility 1.1 / WCAG 2.1 AA (accessibility metadata, declared language, image alt text, navigation, structure) — the checks relevant to the EU Accessibility Act.
Inferred read-onlyfix_epub_accessibilityAutomatically fixes the machine-fixable accessibility issues in an .epub — accessibility metadata, declared language, and AI-written alt text for images — with surgical edits that preserve the publisher's original markup, then re-validates and returns a download link for the remediated .epub plus a report of anything still needing human review.
Inferred read-onlycheck_pdf_accessibilityRuns automated structural accessibility checks on a .pdf against the machine-checkable subset of Section 508 / PDF-UA / WCAG: tag structure, document language, title display, real text layer vs scanned images, bookmarks, and alt text on tagged figures.
Inferred read-onlycheck_docx_accessibilityRuns automated accessibility checks on a Word (.docx) document against the machine-checkable subset of Section 508 / WCAG: document title, declared language, heading structure, image alt text, table header rows, and meaningful link text.
Inferred read-onlycheck_kdp_interior_pdfPreflights a print-interior PDF against the usual Amazon KDP rejection causes: fonts not embedded (the cause of most vague 'does not meet specifications' rejections), page size vs KDP trim sizes (with or without bleed), page count limits (24-828), mixed page sizes, and encryption.
Inferred read-onlyformat_epub_for_printTypesets a reflowable .epub ebook into a print-ready 6x9 paperback interior for Amazon KDP (mirrored margins, real chapter openers from the EPUB's own table of contents) and returns the free preview: title/author/chapters, final page count, and images of the first pages.
Inferred read-onlycheck_kdp_cover_pdfChecks a full-wrap KDP cover PDF against the exact canvas Amazon computes for the book: back cover + spine (from page count and paper type) + front cover + 0.125in bleed.
Inferred read-onlyformat_large_print_editionTypesets a .docx book manuscript into a LARGE PRINT paperback interior for Amazon KDP: 7x10 trim, 16pt body text with generous line spacing — the accessible format for seniors and low-vision readers, and a low-competition second edition of an existing book.
Inferred read-onlycheck_ingramspark_interior_pdfPreflights a print-interior PDF against IngramSpark's stricter requirements — the reasons files that pass Amazon KDP still get rejected there: PDF/X-1a declaration, PDF/X output intent, RGB color objects (Ingram requires CMYK/grayscale), unflattened transparency, unembedded fonts, encryption.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.paperbackkit]
url = "https://paperbackkit.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"paperbackkit": {
"type": "http",
"url": "https://paperbackkit.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: paperbackkit
Remote MCP URL: https://paperbackkit.com/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"paperbackkit": {
"url": "https://paperbackkit.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"paperbackkit": {
"type": "http",
"url": "https://paperbackkit.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "paperbackkit",
"transport": "streamable-http",
"url": "https://paperbackkit.com/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.