"osu!" matching MCP servers:

Enables AI agents to create, execute, and analyze workflows on a Conductor instance through natural language.

Enables Claude or any MCP client to read, create, and edit GoHighLevel workflows through a logged-in Chrome session, with no API key or marketplace app install. Provides 30 tools for workflow CRUD and publishing, step-level patches, folder management, and location data such as tags, users, pipelines, and custom fields.

Turns a real USB HID device — a Raspberry Pi Pico 2 running open-source firmware — into MCP tools (move, click, drag, type, key combos, scroll) for any MCP client. Includes a --mock mode to try every tool with no hardware.

Enables rigging, animation, and VFX workflows for Roblox through an MCP-compatible chat client, connecting Blender and Roblox Studio for tasks like skeleton fitting, keyframe editing, particle effects, and FBX export.

Connects Blender to Claude AI through the Model Context Protocol, enabling AI-assisted 3D modeling, scene creation, object manipulation, and material control. Supports asset integration from Poly Haven and AI-generated 3D models through Hyper3D Rodin.

Enables an AI agent to lease its own Android emulator phone and drive it over stdio: reading the screen, tapping, typing, and opening apps, with every action leaving an audit line and screenshot. Leases keep one agent per phone, and a locked phone stays inert until an operator unlocks it on its own screen.

Enables control of digital mixers (Behringer X32, Midas M32) through natural language commands in Claude Desktop, supporting fader control, muting, EQ, dynamics, effects, scenes, routing, and more via OSC protocol.

Provides a bridge between AI assistants and VRChat, enabling AI-driven avatar control and interactions in virtual reality environments through the Model Context Protocol.

An MCP server that allows Claude models to use Union tasks, workflows, and apps as tools in conversations.

Enables AI coding clients to inspect and invoke local-only tools for an evidence-gated outbound workflow, including buyer selection, mailbox verification, deduplication, factual preflight, and approval-hash checks, with sending disabled by default. It supports synthetic demos and dry-run transports without mailbox credentials, while requiring explicit authorization before any live email action.

Create custom playlists, control apple music locally, search apple music catalog, use ai to generate play lists, and more all without needing an apple developer account or giving the MCP server special privileges.

Enables AI coding assistants to automate live desktop spreadsheet sessions with real-time visual feedback and to create, transform, and extract .xlsx files headlessly. It supports formulas, formatting, charts, PDF export, data analysis, and Markdown/JSON interchange.

Enables reading and writing a running Ableton Live session by creating MIDI, device chains, automation, and arrangement markers while verifying each write by reading it back. It also measures the user's own projects and library to answer with counts and evidence rather than guesses.

Enables AI clients to observe and advance XState actors as MCP tools, including reading current state and context, sending validated events, retrieving transition history, and waiting for target states. It supports per-bridge permissions for state reads, event sending, and resetting, while rejecting events invalid in the current state.

Automatically discovers all scriptable macOS apps and generates MCP tools for them, giving AI access to apps like Mail, Calendar, and Finder without any configuration.

Enables Claude Desktop to trigger Ansible-driven log scans across an inventory group and retrieve combined results from target hosts.

An MCP server that generates images of random dogs from the Dog CEO API with 'LGTM' text overlaid. It allows users to create and save these images to a specified local path through natural language commands.

MCP server that lets Claude read and send WhatsApp messages using a genuine WhatsApp Web client behind a code-enforced human-behavior middleware for safety.