A side-by-side look at the Anymd and TruePath PDF MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Anymd for file systems work as a local process; choose TruePath PDF for file systems as a local process. You can also run both side by side in one mcpServers block.
inspect, outline, read.get_info, extract_text, search.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | File Systems | File Systems |
| Quality signal | 72/100 · Great | 55/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1,046 | 0 |
| Directory activity | 3 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 4 | 9 |
| Full listing | View Anymd | View TruePath PDF |
inspectDocument and media evidence when Markdown is not enough. video_timeline (bounded scene/cue timeline) and render_frame (actual decoded frames), and cite_check (quote/location support, not semantic truth), are anymd Pro; PDF operations: inspect (page facts, metadata), render_page (PNG images), extract_regions (crop bounding boxes), ocr_pages / analyze_regions (configured OCR or vision provider), structure (JSON with document map, elements, geometry; profile quality|research adds trust and accessibility reports), compare (page-level diff of sources[0] vs sources[1]).outlineReturn a document heading tree with stable node ids, title paths, page/slide/chapter ranges and Markdown byte ranges. PDF bookmarks or detected headings, Word headings, PowerPoint slides, EPUB chapters and headings, HTML and Markdown. format json (default) or tree. Pass a node id to read to fetch that section.readRead any document as clean Markdown: PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX/XLS/ODS), CSV, EPUB, HTML or a web URL, Markdown/text, images (metadata + OCR), audio/video (metadata, chapters, subtitles). Pages/slides/sheets carry <!-- page N --> style markers for citation. Long documents stop at max_tokens (default 20000) and end with a cursor to continue; choose pages with pages: "1-5,8". A directory returns its readable files.searchSearch documents for text: one file, many files, whole directories (recursive, .gitignore aware), or URLs, across every format read supports. Returns each hit as file + page/slide/sheet + a snippet with the match in bold. mode auto (default) finds the exact phrase and falls back to BM25-ranked passages when there is none; literal or ranked force one. Narrow directories with glob, e.g. "*.pdf".get_infoPage count, first-page size (with an `allSameSize` flag), encryption status, and embedded PDF metadata (title, author, dates, producer, format version).extract_textPlain-text extraction. Optional 1-based page range (`"3"`, `"1-5"`, `"1,3,5-7"`). Output is grouped by page with `===== Page N =====` markers so the model can cite the right page.searchSubstring search across the whole document. Returns each hit's page, offset within the page, and a snippet of surrounding text. Use for grep-style discovery before a heavier `extract_text`.splitSplit one PDF into N by page ranges. Each range becomes one output file.mergeCombine two or more PDFs into one, in the given order.pagesDelete, rotate, and reorder pages in one pass. `delete` is applied first (page numbers in `rotate` refer to the source PDF); `reorder` is applied to the survivors.to_imagesRasterise PDF pages as PNG or JPG at a chosen DPI. Common DPIs: `96` (screen), `150` (print preview), `300` (print).extract_imagesPull embedded images out of a PDF and write each as a PNG. Reports any images skipped because of unsupported pixel layouts (CMYK, palettized, etc).open_in_truepathHand a local PDF to the TruePath PDF Mac app via `truepath://open?path=…`. Fire-and-forget: macOS launches (or routes to) the app, the URL handler opens the PDF. Use this after reading / analyzing in MCP to drop the user into the GUI for annotation, signing, redaction, etc.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"anymd": {
"command": "npx",
"args": [
"-y",
"@sylphx/anymd"
]
}
}
}
{
"mcpServers": {
"truepath-pdf": {
"command": "npx",
"args": [
"-y",
"@truepathpdf/mcp-server"
]
}
}
}