{"id":"b3afe24b-ee2c-4383-a0bc-3e69a91447fb","shortId":"uNZkcV","kind":"skill","title":"Search large PDFs and read only the relevant pages before answering","tagline":"Use pdf-mcp to inspect a PDF, search it, and load only the pages that matter so an agent can answer questions from long documents without brute-forcing the whole file into context.","description":"# Search large PDFs and read only the relevant pages before answering\n\nUse pdf-mcp to inspect a PDF, search it, and load only the pages that matter so an agent can answer questions from long documents without brute-forcing the whole file into context.\n\n## Prerequisites\n\nPython 3.10+; an MCP-compatible client; local PDFs or accessible PDF URLs; optional extra dependencies for semantic search.\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pip install pdf-mcp\n- pip install 'pdf-mcp[semantic]'\n- brew install tesseract\n- git clone https://github.com/jztan/pdf-mcp.git\n\nRequirements and caveats from upstream:\n- [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n- A [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server that enables AI agents to read, search, and extract content from PDF files. Built with Python and PyMuPDF, with SQLite-based caching for persis...\n- For OCR on scanned PDFs (requires system Tesseract):\n\nBasic usage or getting-started notes:\n- bash\n- For semantic search (adds fastembed and numpy, ~67 MB model download on first use):\n- # macOS\n\n- Source: https://github.com/jztan/pdf-mcp\n- Extracted from upstream docs: https://raw.githubusercontent.com/jztan/pdf-mcp/HEAD/README.md\n\n## Documentation\n\n- https://github.com/jztan/pdf-mcp\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering/)","tags":["search","large","pdfs","and","read","only","the","relevant","pages","before","answering","skills"],"capabilities":["skill","source-agentskillexchange","skill-search-large-pdfs-and-read-only-the-relevant-pages-before-answering","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,518 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:12:21.686Z","embedding":null,"createdAt":"2026-05-18T13:19:13.863Z","updatedAt":"2026-05-18T19:12:21.686Z","lastSeenAt":"2026-05-18T19:12:21.686Z","tsv":"'/)':160 '/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)':153 '/jztan/pdf-mcp':222,233 '/jztan/pdf-mcp.git':143 '/jztan/pdf-mcp/head/readme.md':229 '/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering/)':240 '3.10':95,150 '67':211 'access':104 'add':207 'agent':31,77,166,235 'agentskillexchange.com':239 'agentskillexchange.com/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering/)':238 'ai':165 'answer':11,33,57,79 'base':184 'bash':203 'basic':196 'brew':136 'brute':40,86 'brute-forc':39,85 'built':176 'cach':185 'caveat':146 'client':100 'clone':140 'compat':99 'content':172 'context':46,92,156 'depend':109 'doc':226 'document':37,83,230 'download':214 'enabl':164 'environ':124 'exchang':237 'extra':108 'extract':171,223 'fastemb':208 'file':44,90,175 'first':216 'forc':41,87 'get':200 'getting-start':199 'git':139 'github.com':142,221,232 'github.com/jztan/pdf-mcp':220,231 'github.com/jztan/pdf-mcp.git':141 'img.shields.io':152 'img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)':151 'inspect':17,63 'instal':113,117,126,131,137 'larg':2,48 'load':23,69 'local':101 'long':36,82 'maco':218 'match':122 'matter':28,74 'mb':212 'mcp':15,61,98,129,134,161 'mcp-compat':97 'model':155,213 'modelcontextprotocol.io':159 'modelcontextprotocol.io/)':158 'note':202 'numpi':210 'ocr':189 'option':107 'page':9,26,55,72 'path':120 'pdf':14,19,60,65,105,128,133,174 'pdf-mcp':13,59,127,132 'pdfs':3,49,102,192 'persi':187 'pip':125,130 'prerequisit':93 'protocol':157 'pymupdf':180 'python':94,149,178 'question':34,80 'raw.githubusercontent.com':228 'raw.githubusercontent.com/jztan/pdf-mcp/head/readme.md':227 'read':5,51,168 'relev':8,54 'requir':144,193 'scan':191 'search':1,20,47,66,112,169,206 'semant':111,135,205 'server':162 'setup':119 'skill':236 'skill-search-large-pdfs-and-read-only-the-relevant-pages-before-answering' 'sourc':219,234 'source-agentskillexchange' 'sqlite':183 'sqlite-bas':182 'start':201 'system':194 'tesseract':138,195 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'upstream':116,148,225 'url':106 'usag':197 'use':12,58,114,217 'whole':43,89 'without':38,84","prices":[{"id":"f6c61729-691a-40d3-af35-0d2f706a0b50","listingId":"b3afe24b-ee2c-4383-a0bc-3e69a91447fb","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:19:13.863Z"}],"sources":[{"listingId":"b3afe24b-ee2c-4383-a0bc-3e69a91447fb","source":"github","sourceId":"agentskillexchange/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering","isPrimary":false,"firstSeenAt":"2026-05-18T13:19:13.863Z","lastSeenAt":"2026-05-18T19:12:21.686Z"}],"details":{"listingId":"b3afe24b-ee2c-4383-a0bc-3e69a91447fb","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"search-large-pdfs-and-read-only-the-relevant-pages-before-answering","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"62fc93afe2ec384cbb78cccc2ac4fcf7fa141e7a","skill_md_path":"skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Search large PDFs and read only the relevant pages before answering","description":"Use pdf-mcp to inspect a PDF, search it, and load only the pages that matter so an agent can answer questions from long documents without brute-forcing the whole file into context."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/search-large-pdfs-and-read-only-the-relevant-pages-before-answering"},"updatedAt":"2026-05-18T19:12:21.686Z"}}