# argus-agent mcp

> Talos next · Since next

Connect AI tools: `mcp install --for <tool>`

## Usage

```sh
argus-agent mcp [OPTIONS] <COMMAND>
```

## Commands

| Command | Description |
|---|---|
| `install` | 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). The project's file for that tool unless `--user`; every other server and setting there is kept, a file that changes keeps a timestamped copy beside it, and the change is printed. Tools: claude, codex, cursor, gemini, grok, vscode; `other` prints the config and the command for any other MCP client |

## Options

| Flag | Value | Default | Allowed values | Description |
|---|---|---|---|---|
| `--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 <COMMAND>
```