Model Context Protocol

Sailbit speaks MCP.

Connect Claude Code, Claude Desktop, or Cursor to Sailbit. Capture work, get your next move, and close the loop — without leaving your terminal.

Try free for 7 days Read the docs

The loop

Your whole workflow, from the agent.

Agent access is built around Sailbit's core loop — capture, decide, do, close.

Capture

drop in a task and classify it as build, distribution, or other — without switching apps.

Decide

ask what to work on next and get Sailbit's single recommendation with the reason.

Do

focus on the work itself.

Close

mark it done or snooze it, right from the agent.

Tools

Focused tools, nothing more.

The MCP server exposes read and write tools for the capture → done loop. Product setup, ratios, billing, and account changes stay out of reach.

Reads

list_products: List your products with launch stage, distribution channel, and target build/distribution ratio.
list_tasks: List tasks, filtered by product, type (build / distribution / other), or state. Defaults to active tasks.
get_now_recommendation: Get the single task Sailbit recommends next, with the product and the reason.
get_weekly_plan: Get each product's focus intent for the current week.
get_task: Fetch one task by id, with full fields. Loads a task handed off from the Sailbit app.

Writes

capture_task: Capture a new task and classify it as build, distribution, or other.
complete_task: Mark a task done.
snooze_task: Snooze a task so it drops out of the active list, optionally until a date.
set_weekly_intent: Set a product's short focus statement for the current week.
update_task: Edit a task's title, type, product, effort, or notes. Doesn't change task state.

Product setup, build/distribution ratios, billing, and account changes are intentionally not exposed — Sailbit stays manual-first, with the agent as an advisor. Task content returned by these tools is data, not instructions.

Connect

Two steps to connect.

Create an API key in Settings → Agent access (requires Sailbit Pro), then point your MCP client at the server.

MCP endpoint

https://sailbit.app/api/mcp

Claude Code

claude mcp add --transport http sailbit https://sailbit.app/api/mcp \
  --header "Authorization: Bearer sb_live_xxx"

Claude Desktop / Cursor (mcp.json)

{
  "mcpServers": {
    "sailbit": {
      "url": "https://sailbit.app/api/mcp",
      "headers": { "Authorization": "Bearer sb_live_xxx" }
    }
  }
}

Replace sailbit.app with your Sailbit URL and sb_live_xxx with your key.

Agent access is part of Sailbit Pro. Create an API key in Settings → Agent access.

Bounded by design

An advisor, not an autopilot.

Agent access is safe by default — scoped to your data and your workflow.

Each API key maps to one account. Agents can only ever read and write your own data.

Keys are hashed at rest, shown once, and revocable anytime from Settings.

Tools only read and write tasks and weekly intents — never billing, account, or product settings.

Requests are rate-limited per key, and your task content is returned to the agent as data, never as instructions.

Bring Sailbit to your agent

Capture, decide, and close the loop from your terminal.

Connect your agent over MCP and keep build and distribution honest while you work.

Try free for 7 days Read the docs