PDF Reader MCP vs Unblink
A side-by-side look at the PDF Reader MCP and Unblink MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose PDF Reader MCP for search & data extraction work; choose Unblink for search & data extraction over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose PDF Reader MCP when
- You need dedicated capabilities in the Search & Data Extraction domain.
- Its auth model fits you: No auth required.
- You want tools like
inspect, outline, read.
Choose Unblink when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
read, browse, links.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 65/100 · Great | 52/100 · Good |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Remote HTTP/SSE |
| 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 | 1,041 | 7 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 4 | 18 |
| Full listing | View PDF Reader MCP | View Unblink |
Tools & capabilities
PDF Reader MCP tools 4
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".
Unblink tools 18
readMain content (`mode=article`, default) or whole page (`full`) as Markdown, paginated via cursor. `format=raw_html` returns the unreduced source (optionally scoped by a CSS `selector`) — the escape hatch for scripts/forms/SSR-embedded JSON that reduction strips; `format=text` returns visible plain t…browseCheap orientation: title, description, lang, heading outline, link/form/image counts, excerpt, semantic region map, plus `llms_txt`/`robots` presence hints. Also returns a `collections` inventory — auto-detected repeating record-sets (product lists, search results, table-like rows), each with a rea…linksThe page's links (text + absolute href), optionally filtered. `limit` defaults to 200 (cap 1000); `total`/`truncated` report the rest.formsThe page's forms and their fields (name, type, required, options).findMatching text snippets with the heading path locating each.siteA host's agent-facing metadata: robots.txt summary (allow/disallow for a browser agent, crawl-delay, sitemaps) + llms.txt content + whether llms-full.txt exists. Context only — never blocks a fetch.clickmatch?, render? }submit_formSubmits a form from the current page (cookies carried); returns a summary. Forms declaring `enctype=multipart/form-data` are encoded as multipart automatically; `files` attaches uploads (`{field, filename?, mime?, content \controlsNon-link interactive controls (buttons, `role=button`, `onclick`/`tabindex`, submit/reset inputs, tabs, summaries), each with a stable CSS selector for `interact`.interactDispatches an interaction at a selector and runs the page's JS so its handlers fire, then returns the updated page. `event` defaults to `click`, which emulates a **full primary-button press** (`pointerdown`→`mousedown`→focus→`pointerup`→`mouseup`→`click`) so press/pointer-based widgets (react-aria/…dataMachine-readable structured data embedded in a page: JSON-LD (schema.org), HTML data tables (caption/headers/rows), and microdata (itemscope/itemprop). `kind` selects `jsonld`, `tables`, `microdata`, or `all` (default). HTML only. *(Tables: colspan and rowspan are expanded onto the real grid; micro…extractCaller-directed structured extraction with a CSS-selector schema: `fields` maps each output name to a selector (a string takes the element's collapsed text; `{selector, attr}` takes an attribute value instead). An optional `root` selector emits one record per matching container (e.g. `root="li.prod…- +6 more on the listing page
Ready-to-paste client configs
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.
PDF Reader MCP
No confirmed install command for PDF Reader MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.
Unblink
{
"mcpServers": {
"unblink": {
"url": "https://api.example.com"
}
}
}
Frequently asked questions
PDF Reader MCP is categorized under Search & Data Extraction and uses an install path we have not confirmed yet. Unblink belongs to Search & Data Extraction and uses a remote HTTP/SSE transport. Pick PDF Reader MCP for search & data extraction work and Unblink for search & data extraction.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. PDF Reader MCP has no confirmed install command yet — follow its own setup instructions.
PDF Reader MCP is listed as free. Auth: no auth required. Unblink has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add pdf-reader-mcp and unblink as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, PDF Reader MCP has a quality signal of 65/100 (Great) with 2 views, 0 installs and 1,041 GitHub stars. Unblink has 52/100 (Good) with 1 views, 0 installs and 7 GitHub stars.