"Answer" matching MCP servers:

Enables a chat host to open a blank, dialog-embedded handwriting sheet where users draw answers with a finger, stylus, or mouse, then submit strokes as a replayed PNG plus JSON for optional external grading.

Enables inspecting, creating and modifying MakeHuman characters inside Blender — phenotypes, rigs, assets, skins, faces, expressions and saved presets — through 34 named tools served by a companion Blender bridge add-on that dispatches a closed command vocabulary instead of executing code. It also exposes read-only introspection, catalogue and documentation lookups that always answer, even when Blender is unreachable.

Enables coding agents to turn videos from social platforms or local files into a small set of distinct frames plus a manifest, so they can answer visual questions by reading image paths. Also provides metadata lookup for captions and authors without downloading the video.

Search a YouTube video's transcript and get back only the moments that answer the question, each with a clickable timestamp deep link. Also reads the video's frames — slides, charts, demos and on-screen text — and verifies every citation against recorded evidence before returning it

MCP server for image recognition, supporting multiple vision backends (Anthropic, Zhipu, Ollama) to describe, answer questions, and analyze images.

Enables AI hosts to import PDFs, photos, and exam papers through local stdio MCP tools, using TextIn OCR to build a versioned wrong-answer bank that keeps original evidence and image crops for human review. Supports retrieval, revision history, practice attempts, dated review queues, and printable offline HTML exports of error notebooks, student workbooks, and answer books.

Enables text-only agents to perform local OCR, generate CPU-based image descriptions, and answer boolean, choice, or score visual questions from absolute image paths or text context while returning only agent-facing text and structured data.

A universal vision MCP server that enables Claude Code and Claude Desktop to describe images, extract text, and answer questions about images by converting visual content to text via multiple AI providers.

Enables AI coding agents to inspect digital or scanned PDF forms and worksheets, map detected answer slots through a virtual Excel/Set-of-Marks view, and inject baseline-snapped text, multi-line answers, or option marks into clean output PDFs. Supports visual verification of completed pages.

Enables an AI to generate labeled CT images with answer keys for medical-school practice questions, including click-the-structure hotspot masks that align with the images.

Enables an agent to process local video files and then read, search and inspect the results: timestamped transcripts, on-screen text and key frames as images. Everything runs locally, so an agent can answer questions like how to perform a task shown in a screencast or meeting recording.

Lets agents watch public YouTube videos and answer questions about their audio and visuals, using Gemini for transcript-aware or fixed-frame analysis.

Enables AI agents to analyze and interact with Android phone screens via ADB, using the AutoGLM model to answer queries about screen content and coordinates.

Gives AI coding assistants real-time screen capture capabilities with multi-monitor support, PDF text extraction, and answer logging.

An MCP server that lets Claude Desktop watch videos from YouTube, Instagram, Facebook, or direct URLs, extracting transcripts and key frames to summarize and answer questions about video content.

Enables a cooking assistant to judge readiness from live camera frames, returning proceed, wait, refuse, or abort verdicts through MCP tools so voice assistants and live panels can answer whether an ingredient is ready. It refuses to guess when frames are stale or confidence is low, keeping guidance honest in real cooking conditions.

Turns YouTube videos into a persistent, cross-referenced wiki by combining transcripts with scene-change frame descriptions from a vision model. Exposes that compiled knowledge to MCP clients so their own models can answer questions with sourced citations, without requiring an API key.

Enables MCP clients such as Claude and Copilot to ingest YouTube videos into a persistent, compounding wiki knowledge base by combining transcripts with scene-change vision analysis, then answer natural-language questions by searching the compiled pages and returning candidates and structure for the client's own model to reason over. No API key is required in MCP mode, and knowledge from each new video enriches existing entity, topic, and concept pages.

A desktop tray MCP server that gives text-only LLMs vision by sending images to a multimodal model (e.g., MiMo) and returning the answer, allowing MCP-compatible agents to analyze local images, URLs, or base64 data.

Enables non-multimodal AI models to play Pictionary by turning drawings into structured SVG paths and ASCII grids instead of images. Exposes tools to start a round with an answer and strokes, view the current drawing without spoiling the answer, and submit guesses.