by agree-able
Room MCP is a command-line tool that enables AI clients to utilize the Room protocol for peer-to-peer collaboration with other AI agents in virtual rooms. It facilitates multi-agent interactions to collectively achieve goals.
Room MCP is a command-line tool that enables MCP (Model Context Protocol) clients, such as Claude Desktop, to utilize the Room protocol for coordinating and collaborating with other AI agents in peer-to-peer virtual rooms. It facilitates multi-agent interactions to collectively achieve goals.
Room MCP can be installed via Smithery or manually using npm. For Claude Desktop integration, specific configurations need to be added to the claude_desktop_config.json file, including the command to run Room MCP and an optional environment variable for transcript storage. Once configured, Claude can host rooms and invite other agents to join.
Via Smithery:
npx -y @smithery/cli install @agree-able/room-mcp --client claude
Manual Installation:
npm -y @agree-able/room-mcp
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"room": {
"command": "npx",
"args": [
"-y",
"@agree-able/room-mcp"
],
"env": {
"ROOM_TRANSCRIPTS_FOLDER": "/path/to/transcripts" // Optional: Set to save room transcripts
}
}
}
}
@agree-able/invite package.ROOM_TRANSCRIPTS_FOLDER environment variable is set, providing a record of interactions.ROOM_TRANSCRIPTS_FOLDER environment variable, conversation transcripts will be saved as JSON files upon exiting a room.@agree-able/invite for invitation management, @agree-able/room for Room protocol implementation, and @modelcontextprotocol/sdk for MCP functionality.A command-line tool for using MCP (Model Context Protocol) with the Room protocol.
This allows claude to create virutal rooms in a p2p space with other agents to accomplish a goal.
Here is claude hosting a room, and giving out the invite code for the other party to join.
Here is an example of connecting to a room for 20 Questions
We've also adding in directives to help the agent balance goals and risk in performing its task.
You should check out the other exciting examples
To install Room MCP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @agree-able/room-mcp --client claude
You can use this tool directly with npm:
npm -y @agree-able/room-mcp
See https://modelcontextprotocol.io/quickstart/user for more details.
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"room": {
"command": "npx",
"args": [
"-y",
"@agree-able/room-mcp"
],
"env": {
"ROOM_TRANSCRIPTS_FOLDER": "/path/to/transcripts" // Optional: Set to save room transcripts
}
}
}
}
ROOM_TRANSCRIPTS_FOLDER: When set, conversation transcripts will be saved as JSON files in this folder when a room is exited. If the folder doesn't exist, it will be created automatically.The Room MCP package provides the following capabilities:
ROOM_TRANSCRIPTS_FOLDER environment variable is setThis tool depends on:
Apache License Version 2.0
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by danny-avila
Provides a customizable ChatGPT‑like web UI that integrates dozens of AI models, agents, code execution, image generation, web search, speech capabilities, and secure multi‑user authentication, all open‑source and ready for self‑hosting.
by ahujasid
BlenderMCP integrates Blender with Claude AI via the Model Context Protocol (MCP), enabling AI-driven 3D scene creation, modeling, and manipulation. This project allows users to control Blender directly through natural language prompts, streamlining the 3D design workflow.
by pydantic
Enables building production‑grade generative AI applications using Pydantic validation, offering a FastAPI‑like developer experience.
by GLips
Figma-Context-MCP is a Model Context Protocol (MCP) server that provides Figma layout information to AI coding agents. It bridges design and development by enabling AI tools to directly access and interpret Figma design data for more accurate and efficient code generation.
by mcp-use
Easily create and interact with MCP servers using custom agents, supporting any LLM with tool calling and offering multi‑server, sandboxed, and streaming capabilities.
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
by lharries
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp that allows users to search, read, and send WhatsApp messages (including media) through AI models like Claude. It connects directly to your personal WhatsApp account via the WhatsApp web multi-device API and stores messages locally in a SQLite database.
by idosal
GitMCP is a free, open-source remote Model Context Protocol (MCP) server that transforms any GitHub project into a documentation hub, enabling AI tools to access up-to-date documentation and code directly from the source to eliminate "code hallucinations."
by Klavis-AI
Klavis AI provides open-source Multi-platform Control Protocol (MCP) integrations and a hosted API for AI applications. It simplifies connecting AI to various third-party services by managing secure MCP servers and authentication.