Schema | 5dive MCP server

5dive MCP server

Official

Describes the environment variables required to run the server.

Name	Required	Description	Default
`FIVEDIVE_BIN`	No	Path to the 5dive binary.	5dive
`FIVEDIVE_SUDO`	No	Set to '1' to prefix calls with sudo.
`FIVEDIVE_TIMEOUT_MS`	No	Per-call timeout in milliseconds.	30000

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
task_createA	Create a task in the shared 5dive task queue. Returns the new task's id (e.g. DIVE-N). Use for filing work for an agent or human on the fleet.
task_showA	Fetch full detail for one task by id (numeric or DIVE-N): status, priority, body, result, subtasks, and blockers.
task_listA	List tasks in the shared queue. Defaults to open tasks in priority order; filter by status or assignee.
agent_sendA	Send a message to another agent on the fleet by name (inter-agent comms). The recipient receives it in-session.
agent_listA	List every agent on the box: name, type, channels, model, and live state.
digest_getA	Get the fleet's daily standup digest (activity, token burn, health). Pass window=7d for the weekly view.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/5dive-ai/5dive-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server