Weam
Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents in team or private folders. Modern, fully responsive stack (Next.js, Node.js). Deploy your own vibe-coded AI apps, agents, or workflows—or
What is Weam?
Weam is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to web app for teams of 20+ members. in-built connections to major llms via api. share chats, prompts, and agents in team or private folders. modern, fully responsive stack (next.js, node.js). deploy you...
Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents in team or private folders. Modern, fully responsive stack (Next.js, Node.js). Deploy your own vibe-coded AI apps, agents, or workflows—or
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Web app for teams of 20+ members. In-built connections to ma
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx weamConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Weam
Weam is an open-source, self-hostable team AI chat platform built on Next.js and Node.js that connects to all major LLM providers — OpenAI, Anthropic, Google Gemini, Llama, DeepSeek, Perplexity, and more — through their native APIs. It supports teams of 20+ members with shared prompt libraries, collaborative agent creation backed by knowledge bases, RAG document pipelines, voice-to-text input, and real-time web search. Teams who want to run their own AI infrastructure instead of relying on third-party SaaS platforms deploy Weam to self-host a full-featured collaborative AI workspace.
Prerequisites
- Docker and Docker Compose installed on the deployment host
- API keys for at least one LLM provider (OpenAI, Anthropic, Google Gemini, etc.)
- Git installed to clone the repository
- Node.js 18+ if building without Docker
- An MCP client such as Claude Desktop to connect to the MCP interface when available
Clone the Weam repository
Clone the official Weam repository from GitHub to your local machine or server.
git clone https://github.com/weam-ai/weam.git
cd weamConfigure environment variables
Copy the example environment file and fill in your LLM API keys and any other required configuration values before building.
cp .env.example .env
# Edit .env and add your API keys for OpenAI, Anthropic, etc.Build and start the stack
Use the provided build script (macOS/Linux) or the Windows variant, then bring up all services with Docker Compose.
bash build.sh # macOS/Linux
# bash winbuild.sh # Windows
docker-compose up --buildAdd LLM provider connections
Once the web interface is running (default port 3000), navigate to Settings → Models to add your API keys for each LLM provider you want to use. For local models, install Ollama and set the base URL to http://localhost:11434.
Invite team members and create shared resources
Create team folders to share prompts, agents, and chat histories. Each member gets their own private workspace alongside shared team spaces. Upload documents to the knowledge base to enable RAG-powered agents.
Connect via MCP (when available)
Weam has announced MCP support for Gmail, Slack, and Google Drive integrations. Watch the repository for updates and add the server config once released.
{
"mcpServers": {
"weam": {
"command": "npx",
"args": ["weam"]
}
}
}Weam Examples
Client configuration
Example claude_desktop_config.json entry for Weam once MCP support is released.
{
"mcpServers": {
"weam": {
"command": "npx",
"args": ["weam"],
"env": {}
}
}
}Prompts to try
Sample prompts for the Weam collaborative AI platform after logging in.
- "Create a new shared prompt template for summarising customer feedback emails."
- "Build an agent that searches our knowledge base and answers product questions."
- "Show me all prompts saved in the Marketing team folder."
- "Upload this PDF to the knowledge base and let me ask questions about it."Troubleshooting Weam
Docker Compose fails to start because of missing environment variables
Ensure you copied .env.example to .env and filled in at minimum one LLM provider API key. The DATABASE_URL and auth secrets are also required for the container to start.
Ollama local models are not detected in Settings → Models
Make sure Ollama is running and listening on http://localhost:11434. Set the base URL to that address in Weam's model settings; no API key is required for local Ollama models.
Team members cannot see shared prompts or agents
Check that shared resources were saved to a Team folder rather than a Private folder. Each user must be added to the team in the admin dashboard to see team-level content.
Frequently Asked Questions about Weam
What is Weam?
Weam is a Model Context Protocol (MCP) server that web app for teams of 20+ members. in-built connections to major llms via api. share chats, prompts, and agents in team or private folders. modern, fully responsive stack (next.js, node.js). deploy your own vibe-coded ai apps, agents, or workflows—or It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Weam?
Follow the installation instructions on the Weam GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Weam?
Weam works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Weam free to use?
Yes, Weam is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Weam Alternatives — Similar Communication Servers
Looking for alternatives to Weam? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Weam in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Weam?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.