# PlanWright

Hosted MCP server for agent orchestration. It lets coding models pull objectives from a planning board and signs every workflow step with Ed25519.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 7
- Author: Planwright
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Planwright/planwright
- Updated: 2026-07-04
- HTML: https://affpapa.org/en/nevibecode/mcp/planwright

## What it does

Planwright coordinates developer instructions with autonomous coding tools over Model Context Protocol. Rather than tracking small story points, humans specify high-level goals and acceptance criteria. Agents list scheduled objectives, claim them, break down the technical steps, and submit the outcome for review. The service runs in the cloud at `https://mcp.planwright.tools/mcp`, eliminating local server hosting.

The platform tracks progress using an Ed25519-signed, hash-chained log for all status updates. Agents can also fetch and update repo files such as `CLAUDE.md` to keep requirements synchronized. Running in headless environments or CI requires creating a static token in the web settings, because interactive sessions trigger a GitHub browser login by default.

## Requirements
- Remote server: `https://mcp.planwright.tools/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http planwright https://mcp.planwright.tools/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add planwright --url https://mcp.planwright.tools/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "planwright": {
            "url": "https://mcp.planwright.tools/mcp"
        }
    }
}
```

### GitHub Copilot

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

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http planwright https://mcp.planwright.tools/mcp
```

## When to use it
- assign high-level goals to agents without manually breaking down tasks
- track agent decisions using a cryptographically signed audit log
- feed architecture guides and `CLAUDE.md` into the agent context
- manage execution stages from backlog to human sign-off

## Example prompts
- List all scheduled objectives from Planwright for this project.
- Claim the next objective in the queue and load the context files.
- Submit this task for acceptance and record the code diff.

## 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