Search documents using semantic understanding to find relevant content based on meaning rather than keywords. Understands natural language queries and returns ranked passages with source information.
MIT
631,728 tools. Updated 2026-10-03 01:31
"Searching for documents or information related to PDFs" matching MCP tools:
- List documents in a Needle collection to check processing status, inventory available files, and verify document availability before searching.MIT
- Create a new document collection to organize related documents and enable semantic search across their contents. Returns a collection ID for managing documents.MIT
- Find related documents for any entity by matching amount, vendor, date, or reference. Shows linked and AI-suggested matches.MIT
- Update an existing memory to fix incorrect information after searching. Changes content, project, or memory type and re-computes the embedding.-
- Extract key information from documents using a user-defined schema or auto-generation. Handles PDFs, images, and Office files up to 50MB.MIT
Matching MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.62 npm1MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that provides OpenRouter model pricing data, enabling price lookups, trending/cheapest lists, and model searches without an API key.-
Matching MCP Connectors
Congressional Documents — full-text search and retrieval over the official
High-fidelity PDF to structured Markdown conversion and document field extraction.
- Retrieve relevant information from indexed FHIR documents by searching the Pinecone vector index with a query and document ID.MIT
- Compare two PDFs page by page to detect text differences. Reports identical pages and trimmed diffs for same-layout documents.MIT
- Retrieve text content from OneDrive or SharePoint files using drive and item IDs. Supports Office documents and PDFs, with output truncated to a specified character limit.MIT
- Search for text within wiki-hosted files such as PDFs and text documents. Specify a filename and query to retrieve matches with page or line numbers.MIT
- Lists all PDFs currently loaded in memory, providing an overview of documents available for redaction.MIT
- Read file contents from OneDrive, extracting text from documents, PDFs, spreadsheets, and presentations. Specify a file path to retrieve its content for further processing.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
- Retrieve attached files from Kaltura videos to access supplementary materials like PDFs, presentation slides, or documents. Returns file content or download URLs for specific attachment IDs.MIT
- Perform precise searches across Dutch parliamentary records, including documents, debates, and member information. Filter results using keywords, exact phrases, or advanced operators like 'NOT', 'OR', and 'NEAR()' for accurate topic tracking.MIT
- Refine search queries within Dutch parliamentary data by filtering results to specific content types such as documents, activities, or cases. Use advanced syntax for exact phrases, exclusions, alternatives, or proximity searches to obtain precise results.MIT
- Quickly locate technical details and related content across project documents using intelligent keyword search with result grouping. Ideal for researching before creating new content or verifying existing documentation.-
- Find related medical documents by shared visit dates, diagnoses, or explicit references to support cancer patient care coordination.MIT
- Find documents by topic using semantic search over summaries. Returns titles, headings, and relevance scores to help locate relevant documents before searching for specific content.MIT
- Extract text verbatim from images or PDFs with Gemini multimodal OCR. Returns raw text as Markdown, preserving structure without summarization.Apache 2.0
- Semantically search indexed PDFs to retrieve facts, quotes, definitions, and page citations from specific documents or sections.MIT