# ModelBound MCP server

> Lets an AI client validate, lint, diff, and convert agent skill files across multiple IDEs like Cursor, Claude, and VS Code.

- Repository: https://github.com/ModelBound/modelbound-mcp-server
- Page: https://hostedmcp.org/servers/modelbound/modelbound-mcp-server
- Transport: stdio
- Stars: 1
- License: MIT
- Latest version: 0.1.2

## Install

### Claude Code

```sh
claude mcp add --env 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' modelbound-mcp-server -- npx -y modelbound-mcp
```

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

```json
{
  "mcpServers": {
    "modelbound-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "modelbound-mcp"
      ],
      "env": {
        "MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
      }
    }
  }
}
```

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

```json
{
  "servers": {
    "modelbound-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "modelbound-mcp"
      ],
      "env": {
        "MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"modelbound-mcp-server","type":"stdio","command":"npx","args":["-y","modelbound-mcp"],"env":{"MODELBOUND_API_KEY":"<YOUR_MODELBOUND_API_KEY>"}}'
```

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

```json
{
  "mcpServers": {
    "modelbound-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "modelbound-mcp"
      ],
      "env": {
        "MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add modelbound-mcp-server --env 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' -- npx -y modelbound-mcp
```

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

```toml
[mcp_servers.modelbound-mcp-server]
command = "npx"
args = ["-y", "modelbound-mcp"]

[mcp_servers.modelbound-mcp-server.env]
MODELBOUND_API_KEY = "<YOUR_MODELBOUND_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' modelbound-mcp-server npx -- -y modelbound-mcp
```

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

```json
{
  "mcpServers": {
    "modelbound-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "modelbound-mcp"
      ],
      "env": {
        "MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `MODELBOUND_API_KEY` | no | yes | ModelBound API key for optional cloud sync features. Get one at https://modelbound.co/settings/api-keys |

## FAQ

### Can I use ModelBound without an API key?

Yes, the local tools work without an API key, though cloud features require one.

### What IDEs does it support?

It supports Cursor, Claude, Codex, Kiro, Windsurf, VS Code, and Amazon Q.

### How can I sync my skills across different AI tools?

ModelBound allows you to write a skill once and sync it across different platforms to avoid being locked into one IDE.
