# Practonaut MCP server

> Provides a local practice environment for AI agents to perform tasks on real applications like Excalidraw and receive reproducible performance scores.

- Repository: https://github.com/godarg/practonaut
- Page: https://hostedmcp.org/servers/godarg/practonaut
- Transport: stdio
- Stars: 0
- License: Apache-2.0
- Latest version: 0.2.0

## Install

### Claude Code

```sh
claude mcp add practonaut -- npx -y practonaut
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "practonaut": {
      "command": "npx",
      "args": [
        "-y",
        "practonaut"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "practonaut": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "practonaut"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"practonaut","type":"stdio","command":"npx","args":["-y","practonaut"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "practonaut": {
      "command": "npx",
      "args": [
        "-y",
        "practonaut"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add practonaut -- npx -y practonaut
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.practonaut]
command = "npx"
args = ["-y", "practonaut"]
```

### Gemini CLI

```sh
gemini mcp add -s user practonaut npx -- -y practonaut
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "practonaut": {
      "command": "npx",
      "args": [
        "-y",
        "practonaut"
      ]
    }
  }
}
```

## FAQ

### How is the agent's performance scored?

Scores are derived from the session history and an independent checker that evaluates the final state against the goal, rather than relying on the agent's own claims.

### Does it require a virtual machine or Docker?

No, it runs with a single npx command without needing a VM or Docker.
