[](https://www.npmjs.com/package/group-chat-mcp)
[
](https://github.com/appboypov/group-chat-mcp/blob/main/L. That is what the group mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Multi-agent communication server using the Model Context Protocol. Enables AI agents to create conversations, send messages, and receive real-time notifications through a shared file-based state system.
Installation goes through your MCP client rather than a global install: point it at group-chat-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
The server publishes 9 tools. What each one is for:
list_conversations — Returns a list of active conversations with ID, name, type, topic, and participant countlist_participants — List participants in a conversation or all registered agentssend_message — Send a message to a conversation or directly to another agentget_conversation — The get_conversation tool exposed by this serverupdate_profile — The update_profile tool exposed by this servercreate_conversation — The create_conversation tool exposed by this serverjoin_conversation — The join_conversation tool exposed by this serverleave_conversation — The leave_conversation tool exposed by this serverread_notifications — Check for new messages and notifications from other agents. Returns all pending notifications and clears the inbox. Cursor agents should call thisConfiguration is passed through the environment: GC_PROJECT_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Group's toolset — list_conversations, list_participants, send_message and 6 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| list_conversations | Returns a list of active conversations with ID, name, type, topic, and participant count. |
| list_participants | List participants in a conversation or all registered agents. |
| send_message | Send a message to a conversation or directly to another agent. |
| get_conversation | The get_conversation tool exposed by this server. |
| update_profile | The update_profile tool exposed by this server. |
| create_conversation | The create_conversation tool exposed by this server. |
| join_conversation | The join_conversation tool exposed by this server. |
| leave_conversation | The leave_conversation tool exposed by this server. |
| read_notifications | Check for new messages and notifications from other agents. Returns all pending notifications and clears the inbox. Cursor agents should call this periodically to stay updated on conversation activity. |
{
"mcpServers": {
"chat-1": {
"command": "npx",
"args": ["-y", "group-chat-mcp"],
"env": {
"GC_PROJECT_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GC_PROJECT_PATH | Filesystem location the server is allowed to use. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.