Add documents to a collection by providing a URL for download, processing them for text extraction, and indexing them for semantic search.
MIT
315,865 tools. Last updated 2026-07-28 15:46
"A server for finding PDF documents and files" matching MCP tools:
- Read raw source documents with automatic text extraction for PDF, DOCX, XLSX, PPTX, and plain text. Paginate by pages, sheet, or line offset.MIT
- Convert documents between 100+ formats including Office, PDF, images, and web pages. Accepts local files, URLs, or base64 input without requiring a stored template.Apache 2.0
- Parse local documents (PDF, Word, Excel, HTML) into markdown or structured JSON. Extract content with format selection and PDF-specific options.MIT
- Index local research documents (PDF, Markdown, JSON, TXT) into the Onyx RAG knowledge base. These documents become searchable for instant retrieval and querying.MIT
- Extract figures, tables, and equations from PDF documents using layout detection. Returns base64-encoded images of detected elements with metadata from academic papers or any PDF URL.Apache 2.0
Matching MCP Servers
- Alicense-qualityDmaintenanceStdio MCP server for sandboxed file access — read files, search content, safely edit with checksums, and manage file structure.Last updated5ISC
- Alicense-qualityDmaintenanceA production-ready Model Context Protocol server that bridges local document management with cloud synchronization (Notion) for AI agent integration, enabling seamless access and sync of local and cloud documents.Last updated16MIT
Matching MCP Connectors
Send transactional pdfs for AI agents via SMTP. Templates included.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
- Merge multiple files (PDF, DOC, XLS, images, ZIP) into a single PDF document using URLs or uploaded files.MIT
- Convert scanned PDFs and images into text-searchable documents by running OCR and adding an invisible text layer for full text search.MIT
- Converts KiCad schematic files (.kicad_sch) into PDF format for visual review or sharing, using kicad-cli on the server.Apache 2.0
- Convert local files using the hushvert API: office to PDF, PDF to Word, document interchange, and video transcodes. Returns the output path.MIT
- Split a PDF into multiple documents by specifying page ranges. Each range produces a separate PDF file.MIT
- Convert documents between formats like Markdown, HTML, PDF, and DOCX. Specify content, output format, and complete file paths for advanced formats to transform and save files.MIT
- Upload local document files (PDF, DOC, PPT, XLS, and more) to a Miro board for collaboration.MIT
- Find OneDrive documents using semantic and keyword hybrid search to discover relevant files by topic when exact names are unknown. Returns file metadata, previews, and URLs for analysis.MIT
- Extract basic PDF metadata including page count from local files or URLs, with automatic caching for online documents.MIT
- List and filter documents and files for a building site, including spec sheets, 3D models, BIM files, and maintenance documents to answer questions about available documentation.MIT
- List files stored in the transient workspace directory, enabling access to binary files like documents or spreadsheets for further processing.MIT
- Read text and document files (PDF, DOCX, PPTX, XLSX, ODT, ODP, ODS) with flexible modes: full file, first N lines, last N lines, or a specific line range. Extracts PDF content with format metadata.MIT
- Scans a directory for supported documents (PDF, DOCX, PPTX, TXT, MD, VTT, SRT) and converts each to Markdown, returning an array of conversion results with metadata.MIT
- Find files attached to videos, such as PDFs, slides, or documents, by providing the video ID to retrieve a list of supplementary materials with names, types, and sizes.MIT