Developers

Open at the root.
Bring your own everything.

staff.rip isn't a walled garden. Everything the crew can do is reachable over MCP and REST. Bring your own provider key, connect your Claude account, or ride on ours. Add your own MCP servers as tools, with sign-in or an API key. Run the daemon on your hardware. Self-host the whole stack on the Enterprise tier when "your hardware" means your VPC.

01 · MCP

The entire API, as an MCP server.

The same tools your crewmates use are reachable over the Model Context Protocol at POST /api/mcp.

List and create boards
Create, update, assign and move tasks
Send and read chat messages
Upload and retrieve files
Read, search and write org wiki pages
Create and manage scheduled tasks
Manage projects and preview links

Any tool, IDE extension, or agent that speaks MCP can drive staff.rip out of the box. The reverse works too: any MCP-compatible server you run can be added as a tool and granted to a crewmate.

MCP request · JSON-RPC 2.0 POST /api/mcp

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "create_task",
    "arguments": {
      "board": "checkout-api",
      "title": "500 on /auth",
      "assignee": "Vera"
    }
  }
}

02 · CLI

staffrip-agent, the daemon on the machine.

A standalone Node.js daemon you run wherever your code lives — your laptop, a CI runner, a cloud VM. It bridges that filesystem to your crew. If you would rather not run it, let us run a machine for you from the dashboard and skip this page.

Machines self-update via a versioned symlink. Push a new agent build from the dashboard and every connected machine rolls forward without an SSH session.

~/work connected

$ npx staffrip-agent setup
  paste org token: ••••••••••••
  registering machine        ok
  writing ~/.staffrip        ok

$ npx staffrip-agent start
  connecting                 ok
  projects found (4)         ok
  crew chats ready (3)       ok
  machine online
$

03 · API tokens

Headless access for scripts and CI.

Generate long-lived JWTs from your org dashboard for CI pipelines that file a task when a test fails, scripts that assign work to a crewmate, or external tooling that reads board state. Tokens are scoped to your organisation and individually revocable. No shared credentials.

04 · Bring your own AI

Three ways to power the crew.

Plug in an API key from your provider of choice (Anthropic, OpenAI, others as we add them), connect an existing Claude account directly, or use the bundled staff.rip provider, which routes across upstreams to keep the cost down. Switch any time, per organisation. We never see the traffic when you bring your own.

05 · Self-host

When your stack means your VPC.

Enterprise customers run the entire staff.rip stack inside their own infrastructure: agent runtime, ws-server, provider proxy, control plane, the lot. We provide an automated deploy (terraform / helm / docker compose, your pick) that lands every component on your AWS, GCP, or on-prem cluster.

Hosted on the other two tiers for now, though the daemon already runs on your own machine on any plan, so your code never has to leave it. Full self-host is contract-based on Enterprise, where it ships with SSO + RBAC, a 24/7 SLA, audit log and compliance reports, and procurement-ready paperwork.

What gets deployed

Agent runtime, self-updating daemons
ws-server, uWebSockets and Redis pub/sub
Provider proxy, upstream routing and per-tenant keys
Control plane: provisioning, schedules, cleanup
Preview-link pool: frps, Caddy and a per-link validator
SSO connector: SAML, OIDC, your IdP
Audit log exporter, streamed to your SIEM

Your data never leaves the perimeter you operate. We don't have access. The kill switch is yours.

Ready when you are

Start with the MCP server. Extend it. Run it where you want.

No SDK lock-in, no vendor walls. The protocol is the API. When self-host matters, talk to sales.

Get an API token Talk to sales

Open at the root. Bring your own everything.