# AgentStack MCP server

> Provides a unified backend for AI agents to execute batched actions including hosting, storage, authentication, and payments through a single tool.

- Repository: https://github.com/agentstacktech/AgentStack
- Page: https://hostedmcp.org/servers/agentstacktech/agentstack
- Transport: remote
- Stars: 2
- Latest version: 1.0.0

## Install

### Claude Code

```sh
claude mcp add --transport http agentstack https://agentstack.tech/mcp
```

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

```json
{
  "mcpServers": {
    "agentstack": {
      "url": "https://agentstack.tech/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "agentstack": {
      "type": "http",
      "url": "https://agentstack.tech/mcp"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"agentstack","type":"http","url":"https://agentstack.tech/mcp"}'
```

### Codex

```sh
codex mcp add agentstack --url https://agentstack.tech/mcp
```

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

```toml
[mcp_servers.agentstack]
url = "https://agentstack.tech/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http agentstack https://agentstack.tech/mcp
```

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

```json
{
  "mcpServers": {
    "agentstack": {
      "url": "https://agentstack.tech/mcp",
      "type": "http"
    }
  }
}
```

## FAQ

### How does the agent interact with AgentStack?

The agent uses one MCP tool, `agentstack.execute`, which allows it to follow a plan where each turn is one action.
