"Poly" matching MCP servers:

Enables AI agents to connect to and chat with multiple LLM models (OpenAI, OpenRouter, custom endpoints) with conversation history management and model switching capabilities.

Connects MCP clients to a user's local Chrome profile via a loopback-only WebSocket, adding isolated agent windows, named task groups, workspace cleanup, and explicit human review prompts.

Enables AI agents to run model-checked workflows durably, receiving one work order at a time with guarantees on admission.

Enables browsers to act as MCP servers by relaying tools, resources, and prompts to AI agents via a WebSocket-to-stdio bridge.

Enables LLMs to connect to n8n workflows, Blender 3D, Notion, and filesystem tools through a single MCP hub with hot-pluggable bridges. Features a pedagogical transparency layer for educational purposes and supports multiple LLM providers including Claude, OpenAI, Gemini, and Ollama.