Extract plain text from court filings for reading, summarizing, or quoting content. Supports pagination through long documents with offset and max_chars parameters.
Apache 2.0
599,978 tools. Updated 2026-09-22 10:07
"A tool for summarizing local documents" matching MCP tools:
- Reduce cloud token usage by compressing large text content with a local LLM. Ideal for summarizing logs, files, or verbose context before sending to Claude.Apache 2.0
- Analyze local images for OCR, content extraction, description, comparison, or question answering with a single API call.MIT
- Fetch a local documentation page as plain text and HTML. Supports chunking large documents for easier processing.MIT
- Create a named local vector index for retrieval-augmented generation. Documents added are embedded via Ollama for local RAG without cloud dependencies.-
- Add documents from a local file to the knowledge base for semantic search and retrieval in RAG systems.-
Matching MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows AI assistants to discover, load, and process local documents on Windows systems, with support for multiple file formats and OCR capabilities for scanned PDFs.2-
- AlicenseAqualityBmaintenanceProvides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.2-
Matching MCP Connectors
Congressional Documents — full-text search and retrieval over the official
High-fidelity PDF to structured Markdown conversion and document field extraction.
- Search for documents by content and metadata criteria, narrowing results with filter conditions. Returns only released versions of matching documents.Apache 2.0
- Retrieve complete, untruncated markdown bodies for 1-5 guide IDs obtained from the guide index. Prevents missing-content errors by requiring exact IDs and returns verbatim documents for local use.LGPL 3.0
- Find documents based on their position in a folder hierarchy by providing keywords for each path level. Returns matching document filings.Apache 2.0
- Analyzes documents to automatically create JSON schemas for structured data extraction, enabling consistent field definitions across similar documents.MIT
- Download a full captured session into a secure local artifact for another AI tool. Use when the whole session, including messages, tool calls, results, and diffs, is needed, not a summary.Apache 2.0
- Convert all files in a local directory into structured Docling documents stored in a local cache. Returns cache keys and skips documents already converted, enabling faster reuse.MIT
- Index local research documents (PDF, Markdown, JSON, TXT) into Onyx RAG. Query them via onyx_ask() and onyx_search().MIT
- Replace documents matching a SQL predicate with new rows, one-for-one, using local embeddings when vectors are omitted.Apache 2.0Destructive
- Add documents to a collection by providing a URL for download, processing them for text extraction, and indexing them for semantic search.MIT
- Retrieve a unified list of documents and document groups with filters by status, folder, expiration, and sorting options.MIT
- Download and decrypt attachments—images, voice, videos, documents—from a chat message. Saves a local copy for transcription or other uses.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
- Extract text from images using offline OCR. Reads text from screenshots, documents, and photos via local file paths or base64 data.MIT
- Lists running Revit processes and their active documents, providing document and version details to help select a target instance for subsequent commands.MIT
- Search for documents by name using keywords and optional class filter. Returns matching documents with confidence scores to help select the correct one.Apache 2.0