{"data":{"slug":"sylphxai-pdf-reader-mcp","name":"pdf-reader-mcp","tagline":"PDF intelligence layer for AI agents providing features such as evidence-first extraction and OCR","github_url":"https://github.com/SylphxAI/pdf-reader-mcp","owner":"SylphxAI","repo":"pdf-reader-mcp","owner_avatar_url":"https://avatars.githubusercontent.com/u/206448049?v=4","primary_language":"TypeScript","stars":839,"forks":75,"topics":["agent-document-twin","ai-agent","ai-tools","citations","document-intelligence","document-processing","evidence-first","llm-tool","mcp","model-context-protocol","ocr","pdf","pdf-intelligence","pdf-reader","pdf-to-markdown","rag","rust","trust-report","visual-evidence"],"archived":false,"github_pushed_at":"2026-07-26T16:53:38+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/sylphxai-pdf-reader-mcp","markdown_url":"https://www.graphcanon.com/tools/sylphxai-pdf-reader-mcp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sylphxai-pdf-reader-mcp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sylphxai-pdf-reader-mcp","description":"Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.","homepage_url":"https://sylphxai.github.io/pdf-reader-mcp/","license":"MIT","open_issues":1,"watchers":4,"ai_summary":"SylphxAI/pdf-reader-mcp is an Agent Document Twin designed for AI Agents to handle document intelligence tasks with accuracy and provenance, featuring OCR, evidence-first extraction, and more. It supports Claude, Cursor, VS Code, and any MCP client via the MCP server.","readme_excerpt":"## Install (30 seconds)\n\n```bash\nnpm install -g @sylphx/pdf-reader-mcp\n```\n\nOr pin the current release:\n\n```bash\nnpm install -g @sylphx/pdf-reader-mcp@4.1.1\n```\n\nOne native binary is installed for **your** platform only (not all five).\n\n| Platform | Native package (auto optionalDependency) |\n| --- | --- |\n| macOS arm64 | `@sylphx/pdf-reader-mcp-darwin-arm64` |\n| macOS x64 | `@sylphx/pdf-reader-mcp-darwin-x64` |\n| Linux x64 | `@sylphx/pdf-reader-mcp-linux-x64-gnu` |\n| Linux arm64 | `@sylphx/pdf-reader-mcp-linux-arm64-gnu` |\n| Windows x64 | `@sylphx/pdf-reader-mcp-win32-x64-msvc` |\n\nMissing native package → **fail closed** (no silent engine switch).\n\n---\n\n## Quick start\n\n**Claude Code**\n\n```bash\nclaude mcp add pdf-reader -- npx @sylphx/pdf-reader-mcp\n```\n\n**Claude Desktop / Cursor / VS Code / any MCP client**\n\n```json\n{\n  \"mcpServers\": {\n    \"pdf-reader\": {\n      \"command\": \"npx\",\n      \"args\": [\"@sylphx/pdf-reader-mcp\"]\n    }\n  }\n}\n```\n\n**Stdio / HTTP**\n\n```bash\npdf-reader-mcp\nMCP_TRANSPORT=http pdf-reader-mcp\n```\n\n---\n\n## Install footprint (honest product comparison)\n\nCompare **full clean installs**, not “JS wrapper tarball vs native executable”:\n\n| Metric (measured clean install, **linux-x64**) | Historical TS `3.0.14` | Sole-Rust `4.1.0` |\n| --- | ---: | ---: |\n| Main package on disk | ~403 KB | ~77 KB |\n| Full `node_modules` | ~82.3 MiB | **~24.4 MiB** (~3.4× smaller) |\n| Installed files | 4,101 | **20** (~205× fewer) |\n| Production npm dependency graph | PDF.js + MCP TS SDK + more | `{}` + **one** platform native |\n\nThe native binary is multi-megabyte because it **is** the PDF intelligence engine (parser, server, rendering/table/OCR routing). That is expected and still yields a **cleaner, smaller install** than shipping PDF.js + a JS dependency tree.\n\nDetails: [installed footprint comparison](docs/specs/performance/installed-footprint-comparison.md)\n\n---\n\n## License\n\nMIT\n\n---\n\nIf this saves your agents from PDF hallucinations, **star the repo** and share a demo with your team.","github_created_at":"2025-04-04T16:17:42+00:00","created_at":"2026-07-11T11:54:07.924671+00:00","updated_at":"2026-08-02T04:00:26.97017+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"agent-document-twin","name":"agent-document-twin"},{"slug":"ai-tools","name":"ai-tools"},{"slug":"document-intelligence","name":"document-intelligence"},{"slug":"document-processing","name":"document-processing"},{"slug":"evidence-first","name":"evidence-first"},{"slug":"llm-tool","name":"llm-tool"},{"slug":"model-context-protocol","name":"model-context-protocol"},{"slug":"ocr","name":"ocr"}],"trust":{"provenance":{"is_fork":false,"github_id":960549454,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-27T12:00:24.114Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-07-24T20:02:37Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-08-02T04:00:26.589Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-07-27T12:00:24.614Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-07-27T12:00:24.614Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-27T12:00:24.614Z","managed_saas":false},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-07-27T12:00:24.614Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-07-27T12:00:24.614Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-27T12:00:24.614Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-27T12:00:24.614Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When working within environments that integrate Claude, Cursor, VS Code, or any other MCP client where precision in extracting visual crops and ensuring provenance through OCR is required.","If your AI workflow necessitates trust reports and benchmark-gated releases to maintain high standards of data integrity and reliability."],"when_not_to_use":["For situations where you do not require the specific capabilities like evidence-first extraction or trust reporting that distinguish pdf-reader-mcp from other general OCR tools.","In scenarios where only plain text extraction is needed without advanced features such as document intelligence, visual crops, or PDF to Markdown conversion."],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:08:44.011Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"pdf-reader-mcp acts as an intelligence layer for PDFs to support AI agents in document handling, offering features like evidence-first extraction and OCR with a focus on accuracy and provenance via the MCP server."}]}}