"Collaboration Between Multiple AIs via MCP (Master Control Program)" matching MCP servers:

An orchestration system that breaks down user prompts into actionable tasks and delegates them to specialized agents (Roo Modes) using LangChain.

In-memory MCP server for cooperative collaboration between separate agents, enabling topic-based messaging and coordination via tools like create_topic, join_topic, send_message, read_messages, and check_in.

AI 規格大師 — MCP server bridging specs (Linear / JIRA / GitHub Issues / Notion / Markdown / Figma) to tests, with bidirectional traceability and a spec-quality coach. Sibling to mk-qa-master.

MCP server bridging product ideas to prioritized roadmaps + spec drafts. Hands directly off to mk-spec-master. (AI 規劃大師)

Enables Claude to offload bulk reading, first-draft writing, and mechanical edits to a local or OpenAI-compatible model, with code-enforced verification, staged patches, project checks, and token budgets to save tokens and cost.

A local knowledge graph MCP server that provides AI agents with permanent, structured memory about codebases, enabling semantic search, blast radius analysis, and convention enforcement.

Enables AI agents to interact with collaborative Jupyter notebooks and documents in real-time, supporting notebook operations, document editing, user awareness tracking, and session management through Jupyter's RTC capabilities.

Enables real-time queries about vessels currently near Poole, such as what is on the water, whether a specific ferry is running, and how many boats are moving.

Enables multi-agent code review and iterative improvement loop using different LLM backends, with deterministic scoring and audit trail.

Enables an AI assistant to control a Sonicake Pocket Master guitar processor over USB MIDI by describing tones in plain words — selecting amp/cab/effect models, setting parameters, reordering the signal chain, and saving, renaming, backing up or restoring presets. It also provides offline tools for inspecting firmware and rebuilding it with a translated UI, such as Russian.

Enables AI assistants to create, edit, and export PowerPoint decks through natural language, with live preview, project tracking, and direct browser-based editing.

Centralized MCP server that intelligently routes user queries to appropriate MCP tools, aggregates responses from multiple servers, and supports both rule-based and AI-powered routing.

Deterministic, LLM-first control of Word documents (.docx). An agent reads the outline, finds text by phrase, and applies edits as tracked changes and comments in one atomic batch, with a safety layer that refuses edits based on a stale read and rolls back failed batches. It works on .docx files directly, and can also drive an open document in Microsoft Word on Windows or in LibreOffice Writer.

mcp-test-runner is an MCP server that lets your AI client (Claude / Cursor / Codex / Gemini) drive your entire QA loop end-to-end: * Run tests across pytest / Jest / Cypress / Go / Maestro — single MCP surface, one env var to switch * Analyze a URL (Web DOM probe) or a live mobile screen (Maestro hierarchy) to extract testable modules + candidate cases * Generate runna

Exposes an agent skill, reference guides, and Blender Python script templates over stdio so AI agents can follow a structured modeling workflow and retrieve validation/export resources. It does not itself control a live Blender scene and must be paired with a separate Blender-control MCP server for live operations.

Turns Canvas LMS into a scriptable pipeline and exposes it to AI assistants via MCP for querying courses, grades, assignments, and syncing files using natural language.

Portable governance control-promotion CLI and MCP server.

Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector.

Enables an AI agent or script to control Android TV and LG webOS devices over streamable HTTP, including key presses, app launches, power and wake, input switching, sleep timers, toasts, status checks, screenshots, and device scans, with bearer-token authentication and an app denylist.

Enables local AI clients on Windows to automate desktop and system tasks via MCP stdio, CLI, or optional localhost HTTP, including screenshots, mouse and keyboard input, files, processes, registry, and accessibility-tree window interactions, with local-only execution and no cloud fallback.