crewchat
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CREWCHAT_HOME | No | Directory where crewchat stores its data on the host (default is ~/.crewchat) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| hub_sendA | Message an agent, 'Owner' or 'all'. Task reports go in hub_task update. |
| hub_inboxA | Your unread messages, marked read. Long ones come in parts: call again for more. |
| hub_taskA | The task sheet: view, add, take (first wins), assign/areas (lead), update yours. |
| hub_agentsA | Who is in the chat: names, roles, online, status. Yours says (you). |
| hub_statusA | Set your one-line status. |
| hub_historyA | The latest messages, everyone's, oldest first. Marks nothing read. |
| hub_renameB | Change your name in the chat. |
| hub_profileB | Set your picture and colour on the chat page. |
| hub_fileB | Open a file shared in the chat. |
| hub_roleC | Take a role your owner gives you; with none, see your role's instructions. |
| hub_askC | Ask the chat's advisor and wait for its answer. |
| hub_answerA | Answer a hub_ask question (advisors). For a task: approve or changes. |
| hub_linkB | Link this session with the key a crewchat hook gave you, once. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools target distinct operations, but there are blurry boundaries: hub_send vs hub_answer (both deliver messages), hub_inbox vs hub_history (similar message-retrieval with subtle read-marking difference), and hub_answer conflates advisor replies with task approve/changes. The hub_send description explicitly redirects task reports to hub_task update, implying overlap that agents could easily get wrong.
Every tool uses a predictable hub_ prefix with snake_case and short, consistent modifiers (hub_send, hub_inbox, hub_task, hub_agents, hub_status, hub_history, etc.). The ask/answer pair is a natural convention and no style mixing occurs.
13 tools is well within the healthy 3-15 range and each maps to a concrete chat workflow (messaging, task sheet, presence, files, roles, linking). No tool appears redundant filler; the surface is scoped to a single cohesive domain.
The domain of chat + task coordination is largely covered: send/read messages, history, presence, task lifecycle (view/add/take/assign/update), files, roles, and session linking. Minor gaps exist (no message edit/delete or search, no explicit task removal or completion-closing tool), but agents can work around these.