# DeepStack MCP server

> Provides access to independent analysis of the AI economy, including bull and bear cases, dated investment tests, and macro financial figures.

- Repository: https://github.com/mcauduro0/deepstack-mcp
- Page: https://hostedmcp.org/servers/mcauduro0/deepstack-mcp
- Transport: remote
- Stars: 0
- License: MIT
- Latest version: 1.0.1

## Install

### Claude Code

```sh
claude mcp add --transport http deepstack-mcp https://mcp.deepstack.ltd/mcp
```

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

```json
{
  "mcpServers": {
    "deepstack-mcp": {
      "url": "https://mcp.deepstack.ltd/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "deepstack-mcp": {
      "type": "http",
      "url": "https://mcp.deepstack.ltd/mcp"
    }
  }
}
```

### VS Code CLI

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

### Codex

```sh
codex mcp add deepstack-mcp --url https://mcp.deepstack.ltd/mcp
```

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

```toml
[mcp_servers.deepstack-mcp]
url = "https://mcp.deepstack.ltd/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http deepstack-mcp https://mcp.deepstack.ltd/mcp
```

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

```json
{
  "mcpServers": {
    "deepstack-mcp": {
      "url": "https://mcp.deepstack.ltd/mcp",
      "type": "http"
    }
  }
}
```

## Tools (8)

- `deepstack_search`
- `deepstack_story`
- `deepstack_sides`
- `deepstack_docket`
- `deepstack_results`
- `deepstack_entity`
- `deepstack_tape`
- `deepstack_counter`

## FAQ

### What kind of information does DeepStack provide?

It provides analysis on AI capital, including arguments regarding capex, credit, power, chips, and labs, featuring both sides of a debate and dated tests to settle them.

### Is the DeepStack MCP server free to use?

Yes, the server is free and read-only.

### Does the server provide investment advice?

No, all responses are analysis and opinion only, not investment advice.

### Are there any usage limits?

Yes, there is a limit of 60 requests per minute per session and 30 initialize calls per minute per address.
