# SHIP

Connects your AI client to a team of coding agents that plan, write code, run tests, and open GitHub pull requests from tracker issues.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: letsship
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/letsship/mcp
- Updated: 2026-10-12
- HTML: https://affpapa.org/en/nevibecode/mcp/ship

## What it does

SHIP offloads software delivery tasks to a coordinated group of autonomous agents. The workflow passes through distinct stages: planning, building, reviewing, and testing. Each stage can run engines such as Claude Code or Codex, while your CI pipeline gates the handoffs. Your local assistant can dispatch work and review reports directly from the editor.

The server operates remotely over Streamable HTTP at `https://mcp.letsship.ai/mcp`. It relies on OAuth 2.1 or project-bound bearer tokens for access. Launching a mission takes one credit. Further notes sent to an active mission do not cost extra. If your client supports only stdio transports, bridge the connection via `mcp-remote`.

## Requirements
- Remote server: `https://mcp.letsship.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http ship https://mcp.letsship.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add ship --url https://mcp.letsship.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "ship": {
            "url": "https://mcp.letsship.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "ship": {
            "type": "http",
            "url": "https://mcp.letsship.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http ship https://mcp.letsship.ai/mcp
```

## When to use it
- delegate backlog issues from Linear or Jira to agents
- generate pull requests with automated code reviews and tests
- feed instructions directly to an ongoing background task
- monitor agent progress and inspect verification logs from chat

## Example prompts
- Start a SHIP mission for GitHub issue #84
- Check current mission status using list_missions
- Send an instruction to the active mission: add unit tests for the signup route

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md