# Skylit

Hands an AI agent read-only access to US options flow, volatility, dealer positioning and dark pool prints.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: SkylitAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/SkylitAI/skylit-mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/skylit

## What it does

Skylit is a hosted MCP server, so the repository carries no server code — everything runs on Skylit's side. Clients connect over Streamable HTTP at `https://mcp.skylit.ai/mcp`. Auth works two ways: sign in with Skylit through OAuth, or pass `Authorization: Bearer <API key>` with a key from the developer page.

The catalog lists 68 read-only tools grouped by job: screeners, sweeps and momentum, dark pool, the Heatseeker gamma and vanna heatmaps, the Tempest volatility suite. A smaller intelligence set of five tools (`explain_levels`, `vol_context`, `whats_changed`, `market_brief`, `flow_context`) lives on its own list at `?toolset=intelligence`, which keeps an agent from loading the whole thing. Calls spend credits; the intelligence tools run from 1 to 9 each.

The server is in beta and open to Skylit members who have API access. Without a key or an approved sign-in the tools return nothing, so settle that before wiring up a client.

## Requirements
- Remote server: `https://mcp.skylit.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.skylit.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add skylit --url https://mcp.skylit.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "skylit": {
            "url": "https://mcp.skylit.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "skylit": {
            "type": "http",
            "url": "https://mcp.skylit.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http skylit https://mcp.skylit.ai/mcp
```

## When to use it
- read key dealer-positioning levels for a symbol
- check implied volatility and expected moves before a trade
- see how the positioning board shifted since a given time
- scan for unusual volume and open interest
- review top dark pool prints

## Example prompts
- How has positioning for NVDA moved since this morning?
- Give me the volatility context and scheduled events for TSLA

## Similar
- [tradingview-reader](https://affpapa.org/en/nevibecode/skills/tradingview-reader.md) — skill · 1100 installs
- [stock-scanner-mcp](https://affpapa.org/en/nevibecode/mcp/stock-scanner-mcp.md) — MCP server · ★ 8
- [options-payoff](https://affpapa.org/en/nevibecode/skills/options-payoff.md) — skill · 3400 installs
- [llmquant-options](https://affpapa.org/en/nevibecode/skills/llmquant-options.md) — skill · 488 installs
- [Webull OpenAPI](https://affpapa.org/en/nevibecode/mcp/webull-openapi.md) — MCP server · ★ 30
- [options-strategy-advisor](https://affpapa.org/en/nevibecode/skills/options-strategy-advisor.md) — skill · 3700 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md