Retrieve all OCR (Optical Character Recognition) data for a given asset ID. Enables extracting text from images or documents stored in Immich.
MIT
758,872 tools. Updated 2026-11-08 04:19
"A server for finding information about OCR (Optical Character Recognition)" matching MCP tools:
- Remove hardcoded subtitles from MP4 and MOV videos using OCR technology to detect and erase text while preserving original video content.MIT
- Retrieve detailed information for a specific smart contract security finding using its ID or slug. Access full details on impact, tags, and related data.MIT
- Retrieve detailed character information for Dungeons & Dragons campaigns by providing character name, ID, or player name to access character sheets and game data.MIT
- Search saved knowledge to find specific information about files, fields, or concepts using a case-insensitive query.Apache 2.0
- Extract text from PDF documents (single or multi-page) using Yandex Vision OCR with asynchronous recognition. Supports models for page, table, handwritten, and markdown output.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that provides information about Utkarsh, including bio, skills, work experience, and portfolio projects, accessible via local stdio or remote HTTP with OAuth.6MIT
- AlicenseBqualityBmaintenanceCompress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.31MIT
Matching MCP Connectors
Optical education, prescription transposition, horizontal decentration and approximate prism. PT/EN.
About Bureau, the self-hosted office for AI agents: overview, FAQ search, roadmap, install.
- Check OCR processing status, fetch recognized document lines, and view remaining OCR quota.MIT
- Extract and process images from file paths for visual content analysis, OCR text extraction, and object recognition. Supports screenshots, photos, diagrams, and documents in PNG, JPG, GIF, and WebP formats.MIT
- Extract text from images with Tesseract OCR. Specify language and character limits for accurate results.MIT
- Check Immich server version, feature flags, and version quirks before offering OCR, smart search, or facial recognition. Use it at session start to confirm available features and read-only behavior.MIT
- Re-queue a document for OCR processing when initial OCR failed or the document was updated.MIT
- Retrieve detailed behavioral pattern insights, covering substrate, recognition signals, blind spots, and leverage points for structured analysis.MIT
- Retrieve documentation and type information for a specific position in CodeQL files. Pass file URI, line, and character to get contextual details.MIT
- Retrieve a specified slice of an item's OCR text by character offset, up to 20,000 characters per call. Search full text first to locate the offset you need.MIT
- Extract text from any image in your clipboard using optical character recognition, enabling text-based AI models to read image content without manual saving.MIT
- Retrieve detailed information about a character from OpenArt using its unique ID.MIT
- Retrieve a player's position, inventory summary, character stats, and crafting queue to monitor their status.ISC
- Perform OCR on scanned PDFs to make them searchable. Extract text from image-based PDFs to allow searching and copying.MIT
- Retrieve detailed JSON information about a specific AWS IAM Access Analyzer finding by providing region, analyzer ARN, and finding ID.Apache 2.0
- Extract text from images using optical character recognition. Supports PNG, JPEG, SVG with adjustable detail and model modes for standard or deep document understanding.MIT
- Retrieve the current OCR recognition languages to confirm which languages are configured for text extraction.MIT