"Creating a Local Knowledge Base" matching MCP servers:

基于百度图片搜索API，支持图片搜索、下载及格式转换的MCP服务器。

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

MCP server enabling a florr.io game agent with YOLO vision, entity prediction, combat assessment, and local knowledge base for autonomous gameplay.

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

Extracts timestamped screenshots from local videos, enabling Claude to produce visual walkthroughs without audio analysis or cloud processing.

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.

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.

A MCP server that generates high-quality images using Volcano Engine's JiMeng AI API, supporting various aspect ratios and compatible with different MCP clients.

Enables any MCP-capable agent to generate images in the cloud without a GPU, local models, or downloads, using the user's own API key for providers such as DashScope's Wan/Qwen image models and Volcano Ark's Seedream. It can list which channels are configured and return generated image links or save the files to a local directory, all locally over stdio.

Enables MCP clients to generate and edit images using local Stable Diffusion models in ComfyUI, with tools for text-to-image, img2img, ControlNet, UI frames, upscaling, and background removal—no cloud API or API key required.

该MCP服务器使AI助手（如Claude Code、Codex）能够通过桥接目录和CEP面板与Adobe Premiere Pro交互，支持素材扫描、编辑规划、粗剪执行等操作，强调先规划后执行和人工复核。

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

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.

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

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.

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 AI agents to act as game artists by creating and iterating on game art through MCP tools backed by a knowledge base and genre templates, with a local studio for review, feedback, versioning, and export of engine-ready assets.

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.

fixRAgent triages one photo of a building problem: what it is, how urgent (EMERGENCY, TODAY, THIS WEEK or WHENEVER), which trade to call, and what to tell the resident. Remote server at https://fixragent.com/mcp with three tools: try_sample, assess_property_photo, get_triage_profile. No key needed to start.