Skylit

ai.skylitv0.1.1Updated Oct 1, 2026

Options flow, volatility, dealer positioning (GEX) and dark pool data for AI trading agents.

VerifiedStreamable HTTPWeb executableFinance Data & Analytics

Overview

AI-generated overview

Gives an assistant read-only access to Skylit's US options-market data: options flow, volatility, dealer positioning and dark pool activity.

What it does: Skylit exposes 63 read-only tools over a hosted MCP endpoint, each wrapping one Skylit REST endpoint. Groups cover options flow discovery and feeds, trade and aggregate scores, sweeps and momentum, strike and tide concentration, screeners, bull/bear and pressure ratios, statistics, option chains and charts, market-wide and sector flow, dark pool trades, gamma/vanna heatmaps (Heatseeker) and a volatility suite (Tempest). An account tool reports credit balance and limits.
When to use it: Use it when an assistant needs current US options-market intelligence for research or analysis, such as gamma levels, flow tone, sweeps, volatility surfaces or dark pool prints. It suits research agents that read data; it does not place orders.
Requirements: A remote Streamable HTTP endpoint at Authentication is either OAuth sign-in with Skylit or an Authorization header carrying a Bearer Skylit API key. Access is in beta and limited to Skylit members with API access; calls spend API credits.

Before you install

Calls spend API credits (1 credit = $0.001; typical calls cost 1 to 5 credits), though failed calls are refunded and account_usage is free. The Authorization header carries a personal API key, so keep it private. Tools are read-only and never place orders, but data is licensed for personal trading, research and education; commercial use, redistribution or republishing bulk data needs a written license. Data is market information, not investment advice.

Installation

In SourceWeft

Open Skylit in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.skylit.ai/mcp"
    }
  }
}

README

Skylit MCP

Skylit is the data intelligence platform for AI trading: options flow, volatility, dealer positioning and dark pool data for US markets. The Skylit MCP server gives any MCP client (Claude, ChatGPT, Cursor, VS Code, Gemini CLI, Codex and others) read-only tools over that data.

This repository holds setup guides for each client, the Claude Code plugin, a Gemini CLI extension, an agent skill, and runnable examples. It contains no server code; the server is hosted by Skylit.

Status: beta. The API and MCP server are open to Skylit members with API access. Check yours on the Developer page.

Quick connect


URL	`https://mcp.skylit.ai/mcp`
Transport	Streamable HTTP
Auth	Sign in with Skylit (OAuth): add the URL and approve on the Skylit page. Or send `Authorization: Bearer <API key>` with a key from the Developer page.

Claude Code:

bash

claude mcp add --transport http skylit https://mcp.skylit.ai/mcp# then /mcp -> skylit -> Authenticate

claude mcp add --transport http skylit https://mcp.skylit.ai/mcp# then /mcp -> skylit -> Authenticate

Cursor, LM Studio, Warp and other clients that use an mcpServers JSON file:

json

{  "mcpServers": {    "skylit": {      "url": "https://mcp.skylit.ai/mcp",      "headers": { "Authorization": "Bearer YOUR_SKYLIT_API_KEY" }    }  }}

{  "mcpServers": {    "skylit": {      "url": "https://mcp.skylit.ai/mcp",      "headers": { "Authorization": "Bearer YOUR_SKYLIT_API_KEY" }    }  }}

Leave out headers to sign in with Skylit instead. Field names differ between clients (url, httpUrl, serverUrl, servers), so check your client below.

Then ask: "What are the key gamma levels and today's flow tone for SPY?"

Python

Source and docs: packages/python.

TypeScript

import { Skylit } from "@skylitai/sdk";await new Skylit().gexLevels("SPY");   // reads SKYLIT_API_KEY

import { Skylit } from "@skylitai/sdk";await new Skylit().gexLevels("SPY");   // reads SKYLIT_API_KEY

Source and docs: packages/typescript.

Staying current

This repo is checked against the live API every 6 hours (scripts/sync.py, sync workflow): the tool catalog and REST specs in reference/ are refreshed from Skylit's published docs, and any guide, skill, example or SDK that names a tool or endpoint that no longer exists fails the check and opens an issue.

Clients

Client	Sign in with Skylit	API key	Guide
Claude (claude.ai, Desktop, mobile)	Yes	Desktop, via `mcp-remote`	clients/claude.md
Claude Code	Yes	Yes	clients/claude-code.md
Cursor	Yes	Yes	clients/cursor.md
VS Code / GitHub Copilot	Yes	Yes	clients/vscode.md
Windsurf	Yes	Yes	clients/windsurf.md
Cline	Not documented	Yes	clients/cline.md
Zed	Yes	Yes	clients/zed.md
Gemini CLI	Yes	Yes	clients/gemini-cli.md
Codex CLI	Yes	Yes	clients/codex-cli.md
ChatGPT (developer mode)	Yes	No	clients/chatgpt.md
Goose	Yes	Yes	clients/goose.md
LM Studio	Yes	Yes	clients/lm-studio.md
Raycast	Yes (untested)	Yes (untested)	clients/raycast.md
Continue	Not documented	Yes	clients/continue.md
Warp	Yes	Yes	clients/warp.md
Perplexity	Yes (unverified)	Yes (unverified)	clients/perplexity.md
Any other MCP client, `mcp-remote`, MCP Inspector, raw HTTP	Yes	Yes	clients/generic.md

"Sign in with Skylit" and "API key" reflect each client's own documentation as of 2026-09-30. Guides mark anything we could not confirm.

Tools

63 tools, all read-only. Each wraps one Skylit REST endpoint with the same credit cost. Full catalog with arguments and prices: www.skylit.ai/docs/mcp/tools; machine-readable copy: reference/tools.json.

Group	Tools
Discovery	`flow_search`, `list_active_underlyings`, `expirations`
Scores & trades	`flow_feed`, `trade_score`, `aggregate_score`, `flow_aggregate`
Sweeps & momentum	`sweeps`, `flow_momentum`, `flow_baseline`
Strike & tide concentration	`flow_strikes`, `flow_tide`, `by_strike`
Screeners	`top_underlyings_daily`, `top_underlyings_weekly`, `top_contracts_daily`, `top_contracts_weekly`, `unusual_volume`, `unusual_oi`
Bull/bear & pressure ratios	`chain_bull_bear`, `contract_bull_bear`, `chain_ratio`, `contract_ratio`
Stats, Vol/OI & moneyness	`underlying_stats`, `underlying_bulk_stats`, `contract_bulk_stats`, `underlying_history`, `contract_history`, `flow_historical_compare`, `contract_stats`, `vol_oi`, `moneyness`
Chains, charts & RVOL	`option_chain`, `underlying_chart`, `contract_chart`, `underlying_rvol`, `contract_rvol`
Market-wide & sector	`market_overview`, `market_tide`, `market_breadth`, `sector_flow`
Dark pool	`dark_pool_trades`, `dark_pool_top_prints`
Heatseeker — gamma/vanna heatmaps	`heat_heatmap`, `heat_levels`, `heat_historical_heatmap`, `heat_stats_daily`, `heat_symbols`
Tempest — volatility suite	`tempest_iv`, `tempest_term`, `tempest_cones`, `tempest_sigma`, `tempest_surface`, `tempest_tilt`, `tempest_events`, `tempest_snapshot`, `tempest_market`, `tempest_screener`, `tempest_history`, `tempest_derived`, `tempest_status`, `tempest_symbols`
Account	`account_usage`

Tempest tools depend on your plan; without access they return not_entitled at no charge. OHLCV price bars (Atlas) are available over REST, not MCP.

Pricing

Calls spend API credits: 1 credit = $0.001. A typical call costs 1 to 5 credits.
Failed calls are free: any 4xx or 5xx is refunded.
account_usage is free and returns your balance and limits. Each tool result's meta includes the remaining balance.
Per-tool costs: tool catalog. Plans and included credits: www.skylit.ai/pricing.

REST API

The same data is available over REST with the same key. Each host serves its OpenAPI spec at /v1/openapi.json:

Host	Data
`https://api.skylit.ai`	Dealer positioning (Heatseeker), volatility (Tempest), options flow and dark pool (Flowseeker), account
`https://flow-api.skylit.ai`	Options flow and dark pool (alias for the Flowseeker paths)
`https://atlas-api.skylit.ai`	OHLCV price bars (Atlas)

See examples/python/rest-quickstart and the API reference.

What's in this repo

Path	Purpose
`clients/`	Setup guide per MCP client
`plugins/claude-code/` and `.claude-plugin/marketplace.json`	Claude Code plugin: `/plugin marketplace add SkylitAI/skylit-mcp`, then `/plugin install skylit@skylit`
`gemini-extension.json` and `GEMINI.md`	Gemini CLI extension: `gemini extensions install https://github.com/SkylitAI/skylit-mcp`
`skills/skylit/`	Agent skill on using the tools well: `npx skills add SkylitAI/skylit-mcp`
`examples/`	Research agents: OpenAI Agents SDK, LangChain/LangGraph, Claude Agent SDK, Vercel AI SDK, plain REST
`server.json`	Official MCP Registry entry (`ai.skylit/mcp`)
`llms-install.md`	Install steps for AI coding agents (Cline)

The examples are research agents. They read data and never place orders; order execution is left to your own broker.

Data and licensing

This repository (code and docs) is MIT licensed. See LICENSE and NOTICE. The license does not cover Skylit data.
Skylit data is governed by the API Terms. Keys are personal. Using data for your own trading, research and education, including private agents that act for you, is covered. Commercial use, redistribution and republishing bulk data need a written license: contact [email protected].
Skylit data is market information, not investment advice.

Tools

Tool metadata has not been indexed yet.

Version history

v0.1.1LatestOct 1, 2026

Skylit

Overview

Installation

In SourceWeft

Other MCP clients

README

Skylit MCP

Quick connect

Python

TypeScript

Staying current

Clients

Tools

Pricing

REST API

What's in this repo

Data and licensing

Links

Tools

Version history

More servers like Skylit

Chain of Title

AIDEN

Sec Financial Statements