"Understanding Local File System Operations" matching MCP servers:

MCP server for multimodal understanding and object grounding (bounding boxes) across images, videos, and documents, with support for multiple AI providers (Zhipu GLM-V, OpenAI GPT-4o, Anthropic Claude, or any OpenAI-compatible endpoint).

Enables users to turn GIFs, local videos, and Bilibili videos into timestamped, queryable, and verifiable frame evidence and event timelines, while passing extracted frames to the current session's model instead of calling an external vision API.

An MCP server that uses Google's Gemini API to analyze videos and convert them to text descriptions that Claude Code can understand and act upon.

Enables local MCP-assisted processing of Access database tables, HTML5 advertising ZIP image assets, layered PDFs, and ONIX book-update requests through RapidAPI. It saves results in a selected workspace folder while requiring explicit consent for each processing call.

Local multimodal MCP server for vision, document, audio, video, and GUI automation, all processed locally on Apple Silicon for privacy and security.

Enables MCP clients to generate and edit images through Codex's built-in image generation using a ChatGPT login, returning final files with metadata and optional inline previews.

Enables high-quality 3D-style cartoon image generation using Google Gemini AI alongside secure file system operations like reading, writing, and managing directories. It provides a dual-purpose toolkit for creative asset generation and local file management via the Model Context Protocol.

Local-first MCP server for controlling a loopback ComfyUI instance from same-machine or authenticated LAN clients.

Provides local image understanding for text-only LLMs with tools for image analysis, OCR, object detection, and cropping, all processed on-device.

Lets a text-only LLM read images and PDFs by delegating to a vision model running on your own GPU.

A local (stdio) MCP server for PixelVault — agent-first image hosting, enabling upload of local files by path without base64.

Enables standard stdio MCP hosts to drive a local ComfyUI installation for prompt-based image generation, task status/result retrieval, environment inspection, and VRAM release.

Provides local vision and audio perception for MCP-compatible agents, enabling them to read images, transcribe text from visual media, analyze videos, and convert speech to text entirely on-device. It is privacy-focused with no cloud upload or API keys by default, using Ollama for inference.

An MCP server that integrates with a local ComfyUI, allowing assistants to list and run workflows, monitor progress, and view results, as well as read and edit the live workflow canvas via an optional bridge node.

Enables text-only and offline AI agents to see images through three MCP tools that read UI screenshots, extract verbatim text, and describe images or URLs, returning schema-validated JSON from Gemma 4 running locally via Ollama or through the Gemini API, with optional disk caching so results never leave the machine.

Enables an agent to read, edit, and build Figma designs from scratch — including style guides, variables, components, and screens — through a local plugin bridge to the open file's Plugin API, with no Figma token or REST API calls.

Let me evaluate the README content.

Enables MCP browser agents to locate described UI targets in screenshots through local inference when DOM or accessibility references are unavailable. It shares one localhost-only model across clients, supports lazy loading and screenshot cleanup, and provides health, metrics, and configuration commands.

Enables AI to create and edit local Jianying/CapCut draft projects on macOS from videos, images, audio, and text, supporting editable subtitles, keyframes, motion presets, and batch operations via MCP tools.

Enables controlling GIMP 3 locally through natural language, providing tools for image editing, layer management, selections, and PDB procedure invocation. Keeps all images and files on the user's machine with a local-first, secure design.

Enables Claude Code to call local generative AI services on a LAN, letting users list and chat with Ollama models and list checkpoints, LoRAs, and samplers or generate and save images via Stable Diffusion WebUI Forge Neo. Requests can be made in natural language, with per-call options for model, image size, and Hires.fix settings.

Downloads and analyzes videos from platforms like Instagram, YouTube, and TikTok locally, returning keyframes and optional transcripts.

Enables compatible AI apps to observe and control a locally connected iPhone through stdio MCP tools for screenshots, taps, swipes, long presses, text entry, key and button presses, app listing, and app launching, all reusing the console's device session.

MCP server for local Ollama vision analysis, enabling text-only agents like Claude Code to inspect images via a single tool. Processes images locally with Ollama, keeping image bytes on the machine and returning text reports.

Enables coding agents to ask focused questions about local screenshots, video, audio, and music and receive compact text reports on OCR, layout, timestamps, sounds, and music description. Media stays on the machine and raw files are never loaded into the agent's context, with support for cropping, interval sampling, and durable background jobs.

Enables MCP clients to generate images using local ComfyUI with FLUX.2 Klein models optimized for Apple Silicon, plus model management and system diagnostics.

Enables a local LLM to direct Unreal Engine 5 scenes through verified task-level macros and bounded workflows, applying character animations, measuring poses and foot placement, and capturing evidence while restoring state on failure. It also supports plain-language orders for character actions, crowds, and reference-video generation without requiring a small model to compose hundreds of atomic engine tools.

Privacy-first MCP server for macOS that allows AI agents to search local images using natural language descriptions, leveraging MLX CLIP embeddings and LanceDB for fast, fully offline search.

Enables an AI assistant to convert images among HEIC, JPEG, PNG, WebP, and AVIF entirely on the local machine, including converting a folder of files into a single zip. Access is confined to a user-specified root directory, metadata is stripped by default, existing files are never overwritten, and no network requests or telemetry are used.

A simple MCP server that reads local images and returns them as ImageContent for LLM vision analysis.