Search

https://github.com/matematicsolutions/at-eli-mcp

https://github.com/matematicsolutions/de-eli-mcp

MCP server for PUYUE AI music generation and music tools.

AI codebase health analysis: dead code, circular deps, coupling, architectural drift.

Agent-native MCP server for driving, inspecting, and asserting on real Electron desktop apps.

TrendScout MCP server for research paper, trend, and conference discovery

Enterprise MCP Governor — unified AI tool governance: auth, injection scanning, PII masking, audit logging.

An MCP server that lets any AI assistant consult the q-ching I-Ching oracle as a tool.

Placeholder package — name reserved for mcp-governor project.

Enables cloud LLM agents to discover and invoke physical hardware on edge and IoT devices through standard MCP tools, bridging constrained device channels like UART, BLE, and Wi-Fi.

Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./whisper/client and ./workspace-setup/slug entries. A

MCP tools for the Heroku Platform API: apps, dynos, builds, releases, config vars, addons, teams, spaces, webhooks, and more.

Claude Code subscription auth provider for OpenCode and Claude Code — multiple Claude accounts via OAuth, with subscription rate limits exposed to OpenCode.

CLI-first release gate for AI-built apps

A standalone Model Context Protocol (MCP) server that enables AI assistants (like Claude Desktop) to trigger "Fast Launch" token deployments on Solana via Pump.fun.

Install DragonBot skills (Amazon keyword research, etc.) into your local Claude environment.

See exactly which MCP tools are eating your context window. Disable the deadweight.

MCP server that completes prompts with automatic provider fallback across OpenAI, Anthropic Claude, and Google Gemini. Handles rate limits, transient errors, and missing keys by trying the next provider in chain. Returns first success with full attempt lo

Built-in `plugin` and `provider` tools for managing plugins and LLM providers at runtime — install, remove, reload, and discover.

A working-memory tree CLI for in-flight work.