Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Roboflow (Official)
MCP serversRoboflow computer vision for AI agents: datasets, annotation, versioning, workflows, inference.
-
fiftyone-mcp-server
MCP serversControl FiftyOne computer vision datasets through AI assistants using 80+ operators.
fiftyone-mcp-server@0.1.2 -
MotionLint
MCP serversCatch bad animations before they ship. Deterministic motion audit + vision-LLM design review.
motionlint@0.2.1 -
claude-chat
MCP serversAnthropic Claude Messages API MCP server — chat, vision, web search, extended thinking
-
grok-chat
MCP serversMCP server for the xAI Grok API — chat, vision, search, and embeddings
-
auto-skill-loader
MCP serversAuto-loads skills into agent sessions. MiniMax vision and search proxy.
auto-skill-loader@1.0.1 -
Scout
MCP serversBrowser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.
ghcr.io/felixgeelhaar/scout:1.10.0 -
scholar
MCP serversHardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.
scholar-academic-mcp@1.0.0 -
Perceptdot GA4
MCP serversAI agent vision for Google Analytics 4 — with ROI measurement. perceptdot.com
@perceptdot/ga4@0.2.6 -
Perceptdot Sentry
MCP serversAI agent vision for Sentry error tracking — with ROI measurement. perceptdot.com
@perceptdot/sentry@0.1.5 -
photographi-mcp
MCP serversVisual Intelligence Command Center: A Local Computer Vision Engine for Photo Libraries
photographi-mcp@0.2.6 -
DeepSeek Visionary
MCP serversDeepSeek web vision model as an MCP server with browser auto-login.
https://github.com/xlight/deepseek-visionary/releases/download/v0.2.2/visionary-server-aarch64-apple-darwin.mcpb -
ocular
MCP serversVision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.
ocular-mcp@0.1.0 -
gpt-image2-ppt-skills
SkillsClone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT:gpt-image-2 仿版式、你换内容,另含 10 套精选风格。Claude Code / OpenClaw skill.
git clone https://github.com/JuneYaooo/gpt-image2-ppt-skills.git -
TensorSharp
AI repositoriesA native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability
git clone https://github.com/zhongkaifu/TensorSharp.git -
unstructured
AI repositoriesConvert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
git clone https://github.com/Unstructured-IO/unstructured.git -
Prompt library for ChatGPT Image 2.0 & Nano Banana Pro — 247 prompts, 17 categories.
git clone https://github.com/0aicoder0/Ultimate-ChatGPT-Image-and-Nano-Banana-Pro-Collection.git -
HY-WorldPlay
Modelsimage to video model by tencent · hy-worldplay
tencent/HY-WorldPlay -
animagine-xl-3.1
Modelstext to image model by cagliostrolab · diffusers
cagliostrolab/animagine-xl-3.1 -
Moss-Image-Edit
Modelsimage to image model by chinoll
chinoll/Moss-Image-Edit -
lcm-lora-sdv1-5
Modelstext to image model by latent-consistency · diffusers
latent-consistency/lcm-lora-sdv1-5 -
Flux-Midjourney-Mix2-LoRA
Modelstext to image model by strangerzonehf · diffusers
strangerzonehf/Flux-Midjourney-Mix2-LoRA -
GenPark Multimodal Chart Data Point Extractor
MCP serversCalibrate chart axes and convert bar or scatter pixel coordinates to data values
https://github.com/Alpha-Park/genpark-multimodal-chart-data-point-extractor-skill/releases/download/v1.0.1/genpark-chart-coordinates.mcpb -
text to image model by playgroundai · diffusers
playgroundai/playground-v2-1024px-aesthetic
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.