Camber

By CamberCloud, Inc.

Overview

Camber lets users manage accounts and workspaces, discover or create agents, and launch and monitor agent runs directly within ChatGPT.

Tools

agents_chat_start

ChatGPT

Start a Camber agent chat. This is the tool to use for chatting with an agent. Agent runs can take minutes — longer than MCP tool timeouts allow (Claude Desktop cannot extend them). So this tool does NOT wait for the reply: it submits the message and returns immediately with a conversation_id and a clickable chat_url. The agent keeps working on the server after this returns. You MUST follow up, the reply is NOT in this tool's result: 1. After calling this tool you MUST tell the user the work is in progress and share the chat_url as a markdown hyperlink ([Open live chat](chat_url)) never a bare URL so it renders clean and clickable in both terminal and clients. 2. Then immediately call the `agents_chat_status` tool with the returned conversation_id to get the agent's reply. That tool checks twice over 30 seconds, if the latest status is running, call it again. MUST NOT end your turn until agents_chat_status returns status idle (done) or failed. One run per conversation: continuing a conversation_id that is still running fails with a "still generating a response" error. Either wait and retry after agents_chat_status reports it finished, or call again with stop=true to interrupt the current run and send the new message.

agents_chat_status

ChatGPT

Check an async agent chat started with agents_chat_start, and return its reply when done. This checks the Camber agent run twice over 30 seconds and returns its latest status. Status values: - running: still working — call this tool again with the same conversation_id. - idle: finished — content holds the agent's reply. - failed: the run errored. Returns: AgentChatStatus with status, content (the reply once done), and output_stash_files. The run may reference output files in Camber Stash (stash://...). Those live in the cloud until copied locally: camber stash cp stash://<user>/<path> ./<local> (see camber stash cp --help), then confirm with the user where files were saved.

agents_create

ChatGPT

Create a Camber agent. Creates a personal agent by default. Pass team_name to create the agent for a team you belong to. Returns the created agent, including its tag.

agents_list

ChatGPT

List Camber agents with optional scope and pagination. Returns: AgentListInfo object containing: - data: List of AgentInfo objects - page: PageInfo object with pagination details (page, size, total, num_page)

teams_list

ChatGPT

List the authenticated user's teams and personal workspace. Returns display names, unique names, workspace type, and selected status.

teams_select

ChatGPT

Select the active user team or personal workspace. Provide exactly one of team_name or personal=true. Changing workspaces may stop an active Jupyter server in the previously selected workspace.