DicePDF MCP server
io.github.ishan-maheshwari/dicepdf·v0.1.0Local-first PDF tools for AI agents: merge, split, extract, render, compress. Files stay on-device.
19 downloads/wk
Reviews
Write oneNobody has reviewed DicePDF yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
DicePDF tools (11, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
pdf_add_page_numbersStamp page numbers onto every page of a local PDF.
pdf_compressCompress a local PDF. Default mode is structural (lossless, keeps text); set aggressive to rasterize pages for much smaller scan-heavy files.
pdf_delete_pageswrite actionRemove the given 1-based pages from a local PDF.
pdf_extract_textExtract text from a local PDF as plain text, Markdown, or JSON. The file is read from disk and never uploaded.
pdf_mergeMerge multiple local PDFs into one, in the given order. Files stay on disk.
pdf_metadataReport page count, AcroForm presence, and signature flag for a local PDF.
pdf_rotateRotate all (or selected) pages of a local PDF by 90/180/270\xB0.
pdf_splitSplit a local PDF by page ranges, specific pages, or into every page. Outputs are written to a directory.
pdf_strip_metadatawrite actionRemove Title/Author/Producer/XMP and the document ID from a local PDF.
pdf_to_imageRasterize a local PDF to PNG or JPEG images, one file per page, written to a directory.
pdf_watermarkStamp a text watermark across every page of a local PDF.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
How DicePDF compares
Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 65/100
- higher than 20% of 866 Scraping and browsing servers
- Tools
- 11
- the typical Scraping and browsing server has 6
- Tools that change things
- 18%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 19
- more than 4% of 309 Scraping and browsing servers with a package
What its tools let an agent do: 9 read · 2 change
Install DicePDF in Claude Code, Cursor or VS Code
Runs npx -y @dicepdf/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add dicepdf -- npx -y @dicepdf/mcp
DicePDF: common questions
- Is DicePDF MCP server safe?
- With care: it is graded C, so read the findings first (65/100). Read the DicePDF safety report
- How do I install DicePDF?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does DicePDF need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is DicePDF maintained?
- The latest release is v0.1.0.
- What can I use instead of DicePDF?
- Servers from other publishers that do the same job: AgentRender MCP server, Rendex: Rendering API for Images, PDFs & Content Extraction MCP server and Kitewright MCP server.
- How does DicePDF compare with other Scraping and browsing MCP servers?
- safety score 65/100 (higher than 20% of 866 Scraping and browsing servers); tools 11 (the typical Scraping and browsing server has 6); tools that change things 18% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to DicePDF
Same job from other publishers: the closest match first, then the best rated.
AgentRenderURL to screenshot, PDF, or extract for AI agents. Free 150 renders/mo, then $17/mo.not reviewedGrowingA- Rendex: Rendering API for Images, PDFs & Content ExtractionRender HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.not reviewedGrowingA
- KitewrightLightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.not reviewedGrowingA
Numbers-LEExtract numeric values from config files, data files and plain text.not reviewedGrowingA- BrightdataBright Data's Web MCP server enabling AI agents to search, extract & navigate the webnot reviewedEstablishedB