Saiki

Creative AI art engine designed for unique style transfers and instant visual magic.

SEO research tools for AI agents: keyword research and metrics, SERP and local SERP results, domain and backlink analysis, rank tracking, and Google Search Console performance.

Open-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.

GPT Image 2 AI is an MCP-compatible service for generating and transforming images using text prompts. It provides a simple interface for AI agents and developer tools to create visual outputs, refine images, and experiment with generative workflows in a programmatic way. The service is designed to be lightweight and easy to integrate into MCP-based environments, enabling use cases such as: text-to-image generation image refinement and variation visual prototyping workflows AI-assisted content pipelines 👉 https://gptimg2ai.net This server can be used by AI agents to generate visual assets dynamically, making it suitable for creative tooling, automation workflows, and experimental AI applications.

The second fastest AI chatbot™

DOHOO is an AI-native social media management platform that lets you publish, schedule, and automate content across 8 platforms simultaneously — TikTok, Instagram, Facebook, YouTube, X (Twitter), Threads, LinkedIn, and Pinterest. With the DOHOO MCP connector, Claude can: - Schedule and publish posts, images, videos, and carousels to any connected social account - Manage 40+ social profiles from a single session - Upload media to DOHOO storage and get permanent CDN URLs - List, organize, and reuse media files and folders - Check scheduled post status and publishing history - Trigger multi-platform publishing workflows in one command Built for SMM specialists, agencies, and founders who want to run their entire social media operation directly from Claude — no switching tabs, no manual copy-paste. Connect once. Publish everywhere.

Your Data. Your AI. Your Rules. Ontheia is a self-hosted, open-source AI agent platform. Run AI agents, automate workflows, and connect AI models to any tool — entirely on your own infrastructure, without sending data to external cloud services.

Explyt is an IDE-native AI agent for JetBrains IDEs. It helps developers code, test, debug, refactor, review changes, and fix issues with real IDE context, including project structure, symbol navigation, run configurations, debugger state, inspections, and coverage data. Explyt supports MCP and AGENTS.md for portable AI workflows, making JetBrains IDEs available as a powerful context and tools layer for AI-assisted software development.

AI GPT Image is an online GPT Image 2 AI image generator and editor that helps users create, edit, upscale, and transform images with text prompts and reference photos. It supports text-to-image generation, image-to-image transformation, natural language image editing, AI image upscaling, and AI video creation workflows. Powered by GPT Image 2, AI GPT Image is designed for high-quality visual creation with stronger prompt understanding, improved text rendering, multilingual visual design, realistic lighting, detailed textures, and better style consistency. Users can create realistic portraits, product photos, YouTube thumbnails, social media graphics, posters, UI mockups, infographics, character concepts, cinematic storyboards, and commercial design assets in just a few steps. AI GPT Image is suitable for creators, designers, marketers, e-commerce sellers, bloggers, YouTubers, startup teams, indie hackers, AI creators, and anyone who wants to generate professional images online without complex design software. It is especially useful for social media content, advertising creatives, product marketing, blog covers, visual storytelling, image editing, and AI image-to-video workflows.

Fast, intuitive AI image generation platform for everyday creative inspiration.

A Tiny Terminal Chat App for AI Models with MCP Client Support

devops-mcp lets AI assistants (Claude Desktop, Cursor, Windsurf) connect, scan, plan, and deploy on real Linux servers — without handing the model the keys to the kingdom. Reading is always allowed; anything that changes state on a production-like server is refused unless the user pastes a secret elevation token the model never sees. Three modes (SAFE / PROVISION / FULL) with auto-expiry, a production write-gate that demands backup confirmation for irrecoverable ops, shell-quoted arguments, prompt-injection-tagged output, and a full JSON-lines audit log. 32 tools, TypeScript, MIT.

Private, free, open-source local AI chat and MCP host. Run 1000+ LLMs on your device, connect any MCP server (STDIO, HTTP, SSE) and use tools with local or cloud models - no cloud API required

Overreach catches AI-agent scope creep. You give it the prompt you gave your coding agent and the diff it produced; it flags every part of the diff the prompt didn't authorize — unauthorized dependencies, env vars, endpoints, cron jobs, files, and features. Every finding is deterministic set arithmetic (actual − authorized), not a probabilistic opinion. Ships a GitHub Action that fails PRs on scope_creep_score=HIGH. MIT, free to use.

Visual Studio Code

Local MCP server exposing iGPSport cycling data to LLM clients. Computes training metrics (NP/IF/TSS/CTL/ATL/TSB) server-side, supports 17 tools including activity analysis, segment leaderboards, workout generation, and threshold estimation.

The new purpose-built IDE to harness magic

A local-only macOS Model Context Protocol server that exposes your Proton Mail account to Claude Desktop and Claude Code via Touch-ID-gated tool calls.