# argus-agent mcp install

> Talos next · Since next

Connect an AI tool to a project in one step: write this agent server into the tool's own MCP config, in its own shape (docs/CONNECT-ANY-AI.md).

## Usage

```sh
argus-agent mcp install [OPTIONS] --for <TOOL>
```

## Options

| Flag | Value | Default | Allowed values | Description |
|---|---|---|---|---|
| `--for` | `<TOOL>` |  |  | The tool: claude, codex, cursor, gemini, grok, vscode, or other |
| `--project` | `<PROJECT>` |  |  | The project folder (or its argus.project.json). The current folder when absent |
| `--user` |  |  |  | Write the tool's user-wide file (in your home folder) instead of the project's |
| `--from` | `<SIDE>` |  |  | Where the tool runs: `windows` (the default on Windows) or `wsl` (a tool inside WSL starting this Windows engine) |
| `--dry-run` |  |  |  | Print the change and write nothing |
| `--print` |  |  |  | Print the tool's config entry and the one-line command, and write nothing |
| `--tool-names` | `<TOOL_NAMES>` | `dotted` |  | How `tools/list` spells the names. `dotted` is the interface's own (`scene.read`); `underscore` is for a client that namespaces a tool into an identifier and will not take a dot (`scene__read`); `hyphen` for one that also takes no `__` inside a tool's name (Grok: `scene-read`). `tools/call` takes any spelling whichever this is |
| `--toolsets` | `<TOOLSETS>` | `""` |  | Toolsets to list from the start, beyond the core: comma-separated names, or `all`. For a client that does not refetch `tools/list` when told it changed; one that does can call `tools.enable` instead and pay for the tools only when it needs them. ARGUS_AGENT_TOOLSETS when absent, so a harness can set it for every server it starts |

## Example

```sh
argus-agent mcp install --for <TOOL>
```