MCP server

Provides a unified control plane for AI agents to operate digital content creation tools, game engines, and design software through a single protocol.

Provides AI agents with structured control over Linux desktops using semantic accessibility trees, window targeting, and input synthesis.

Allows AI agents to query over 100 different databases using pre-configured connections.

Search local screen recordings, audio transcriptions, and computer activity to control your computer with AI.

A local-first search engine and MCP server that indexes code, docs, and logs to provide cited answers and agent memory for AI clients.

Turns web pages into clean markdown, JSON, or LLM-ready text and lets AI clients scrape, crawl, search, and extract structured data from websites.

Lets an AI client discover and control TP-Link Tapo smart home devices including lights, plugs, cameras, and sensors.

Coordinates parallel coding agents by detecting semantic intent conflicts before they result in code collisions.

Converts URLs into clean markdown or structured JSON through web scraping, crawling, mapping, and searching capabilities.

Enables AI clients to generate, edit, inpaint, and upscale images offline using Qwen-Image 2.1 on your local GPU.

Provides AI agents with persistent cognitive memory using semantic search, Hebbian learning, and knowledge graphs.

Gives AI agents entity-level code intelligence to find definitions, analyze change impact, run checks, and certify reviews in a Git repo.

Provides a local-first security layer for AI agents to review shell commands, file access, package installs, and MCP tool calls before execution.

Lets an AI client run Windmill scripts and flows and manage jobs, schedules, resources and variables in a workspace.

Performs semantic search across Sui documentation and knowledge sources using kapa.ai.

Provides a shared Markdown-based knowledge base that acts as a persistent memory for AI agents and human collaborators.

Enables AI agents to perform Bloomberg request/response workflows including reference data, historical data, and Bloomberg Query Language (BQL) requests.

Enables AI agents to perform Bloomberg request/response workflows including reference, historical, bulk, and intraday data retrieval.

Provides long-term persistent memory for AI coding agents using a knowledge graph with hybrid search and procedural memory.

Analyzes TypeScript and JavaScript codebases to detect complexity, duplication, architecture drift, and unused code using a repository graph.