{"id":50472503,"url":"https://github.com/hannasdev/mcp-document-reader","last_synced_at":"2026-06-01T11:04:19.072Z","repository":{"id":349440342,"uuid":"1201846461","full_name":"hannasdev/mcp-document-reader","owner":"hannasdev","description":"MCP server for reading large PDF documents — paginated reads, full-text search, and page-aware navigation for AI assistants.","archived":false,"fork":false,"pushed_at":"2026-04-05T09:00:55.000Z","size":19,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-06T01:20:09.900Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hannasdev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-05T08:45:09.000Z","updated_at":"2026-04-05T09:00:59.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/hannasdev/mcp-document-reader","commit_stats":null,"previous_names":["hannasdev/mcp-document-reader"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/hannasdev/mcp-document-reader","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannasdev%2Fmcp-document-reader","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannasdev%2Fmcp-document-reader/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannasdev%2Fmcp-document-reader/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannasdev%2Fmcp-document-reader/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hannasdev","download_url":"https://codeload.github.com/hannasdev/mcp-document-reader/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hannasdev%2Fmcp-document-reader/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33771641,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-01T02:00:06.963Z","response_time":115,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-01T11:04:18.101Z","updated_at":"2026-06-01T11:04:19.062Z","avatar_url":"https://github.com/hannasdev.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# mcp-document-reader\n\nMCP server for AI-assisted PDF reading with pagination, search, and page navigation.\n\nDesigned to let AI assistants read large documents without filling the context window from page 1 every time. The model can chunk through a book, jump to any section by keyword, and pick up exactly where it left off.\n\n## Tools\n\n| Tool | Description |\n|---|---|\n| `list_documents` | List all documents in the configured directory |\n| `get_document_info` | Get page count and file size without extracting text |\n| `read_document` | Read a page range (default: 50-page chunks) |\n| `search_document` | Keyword search — returns page numbers and context snippets |\n\nEvery `read_document` response includes a `[Pages X–Y of Z total]` header and a continuation hint so the model knows exactly where to call next.\n\n## Quick start (Claude Desktop / npx)\n\nAdd to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):\n\n```json\n{\n  \"mcpServers\": {\n    \"documents\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@hanna84/mcp-document-reader\", \"--stdio\", \"--dir\", \"/path/to/your/docs\"]\n    }\n  }\n}\n```\n\nNo install needed — `npx` pulls the package on first run.\n\n## Self-hosted (Docker / SSE)\n\n```yaml\n# docker-compose.yml\nservices:\n  mcp-document-reader:\n    image: node:22-alpine\n    working_dir: /app\n    command: node index.js\n    environment:\n      DOC_DIR: /docs\n      HTTP_PORT: \"3000\"\n    volumes:\n      - ./docs:/docs:ro\n    ports:\n      - \"3000:3000\"\n```\n\nRegister the SSE endpoint in your MCP gateway:\n```json\n{ \"url\": \"http://mcp-document-reader:3000/sse\" }\n```\n\nA `GET /healthz` endpoint is available for Docker healthchecks.\n\n## CLI reference\n\n```\nnode index.js [options]\n\n  --dir \u003cpath\u003e    Directory to serve documents from  (default: $DOC_DIR or cwd)\n  --port \u003cn\u003e      HTTP port for SSE mode             (default: $HTTP_PORT or 3000)\n  --stdio         Use stdio transport instead of SSE\n```\n\n## Environment variables\n\n| Variable | Default | Description |\n|---|---|---|\n| `DOC_DIR` | `.` | Document directory |\n| `HTTP_PORT` | `3000` | SSE server port |\n| `MCP_TRANSPORT` | — | Set to `stdio` to use stdio transport |\n\n## Supported formats\n\n- PDF (`.pdf`)\n\n## Requirements\n\nNode.js \u003e= 18\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhannasdev%2Fmcp-document-reader","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhannasdev%2Fmcp-document-reader","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhannasdev%2Fmcp-document-reader/lists"}