# plori

Remote MCP server that connects your agent to Plori cloud workspaces, coordinating multi-agent collaboration with revisions.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: plori-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/plori-ai/plori
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/plori

## What it does

Plori coordinates artificial intelligence agents inside cloud workspaces. Each task worker experiments on its own workspace clone, while the platform merges changes once runs complete. Because all project files remain hosted in the cloud, agents cannot read or modify files on your local drive.

The service connects as a remote streamable HTTP endpoint at `https://api.plori.ai/mcp` without local runtimes. Its API provides 24 tools split into five functional sets: tracking workspace revisions, dispatching runs, checking credit consumption, launching workers, and inspecting pending human inputs.

Direct approval of risky steps is blocked inside the MCP client. Instead, each suspended action issues an `approve_url` that you confirm manually inside the Plori dashboard. Headless sessions bypass browser-based OAuth 2.1 via an API key passed in request headers.

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

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- orchestrate collaborative AI workers across isolated workspace copies
- merge file updates from parallel agent runs automatically
- monitor token consumption, run status, and remaining credit balances
- read and upload workspace files remotely through MCP tools

## Example prompts
- List my Plori workspaces and display the remaining credit balance.
- Spawn a new workspace worker to investigate the project repository.
- Retrieve pending approval requests and display their confirmation links.

## Similar
- [delegate-setup](https://affpapa.org/en/nevibecode/skills/delegate-setup.md) — skill · 5900 installs
- [arena](https://affpapa.org/en/nevibecode/skills/arena.md) — skill · 5900 installs
- [Swarm Orchestration](https://affpapa.org/en/nevibecode/skills/swarm-orchestration.md) — skill · 2100 installs
- [open-prose](https://affpapa.org/en/nevibecode/skills/open-prose.md) — skill · 2000 installs
- [ai-agents-architect](https://affpapa.org/en/nevibecode/skills/sickn33-ai-agents-architect.md) — skill · 1500 installs
- [paperclip-ai-orchestration](https://affpapa.org/en/nevibecode/skills/paperclip-ai-orchestration.md) — skill · 1500 installs

---
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