5dive-ai/5dive-mcp

Expose the **5dive** agent-fleet CLI as Model Context
Protocol tools. Point any MCP client (Claude
Desktop, Cursor, Cline, or your own) at this stdio server to file tasks, inspect
and message agents, and read the fleet digest — directly from inside a model
context.
5dive is the CLI + control plane for running a fleet of
autonomous coding agents as a self-governing company. This server is a thin,
honest adapter: every tool shells out to the local 5dive binary's
machine-readable --json surface and returns the result — so it inherits the
CLI's auth, permissions, and audit log for free, and never handles secrets itself.
Tools
| Tool | Wraps | What it does |
| --- | --- | --- |
| task_create | 5dive task add | File a task in the shared queue (title, body, priority, assignee, parent). |
| task_show | 5dive task show | Full detail for one task by id (status, body, result, subtasks, blockers). |
| task_list | 5dive task ls | List tasks (open by default; filter by status / assignee). |
| agent_send | 5dive agent send | Send a message to another agent on the fleet. |
| agent_list | 5dive agent list | List every agent: type, channels, model, live state. |
| digest_get | 5dive digest | Fleet daily standup digest (window: "7d" for the weekly view). |
Requirements
- Node.js >= 18
- The 5dive CLI installed and on PATH (curl https://install.5dive.ai | sudo bash).
Install & run
Client config (Claude Desktop / Cursor / Cline)
Remote mode: 5dive-mcp serve (ChatGPT, OpenAI dots)
A client that runs in someone else's cloud can't spawn a stdio process on your
box. serve puts the same six tools behind MCP's Streamable HTTP transport, on
loopback, for your reverse proxy to publish over HTTPS.
> Using **managed 5dive**? You don't need this: connect to
> https://api.5dive.com/mcp and sign in. See
> the guide.
Then point the client at it:
- **Clients that can send a header** (Claude Code, the MCP inspector, most SDKs):
https://agents.example.com/mcp with Authorization: Bearer .
- **ChatGPT developer mode** offers only OAuth or "No authentication", so put
the token in the URL and choose "No authentication":
https://agents.example.com/mcp/ .
5dive-mcp token list shows the tokens; 5dive-mcp token revoke --name=chatgpt
cuts one off, and a running server refuses it from the next request.
| serve flag | Default | Purpose |
| --- | --- | --- |
| --listen | 127.0.0.1:8741 | Address to bind. A non-loopback address is refused unless you pass --allow-public-http. |
| --path | /mcp | Mount point. |
| --rate | 60 | Tool calls per token per minute. |
Security: what opening this endpoint means
- **What a token can do.** A read-only token can list agents and tasks, read a
task, and read the digest. A --write token can also file tasks
(task_create) and message agents (agent_send). No token can answer a gate,
change settings, spend money, or run anything outside those six CLI calls,
each built as a fixed argv with no shell. Whatever sender the remote client
claims is dropped: its messages arrive labelled mcp- , and its
tasks say in their body which connection filed them.
- **Who it runs as.** The tools run with the rights of the user running