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:

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:

{
  "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

pip install skylit

from skylit import Skylit
Skylit().gex_levels("SPY")   # reads SKYLIT_API_KEY

Source and docs: packages/python.

TypeScript

npm install @skylitai/sdk

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.

Intelligence toolset

One-call answers for agents, each with a short factual summary, compact data and meta (cost, balance, asOf, partial). They have their own tool list, so an agent loads only these:

https://mcp.skylit.ai/mcp?toolset=intelligence

Tool	Answers	Credits
explain_levels	Key dealer-positioning levels for a symbol	1
vol_context	Implied volatility, IV rank, expected moves, scheduled events	2
whats_changed	How the positioning board moved since a given time	6
market_brief	VIX complex, market-wide options flow, SPX and QQQ levels	5
flow_context	Today's options flow read for a ticker	9

Details: Intelligence tools.

Tools

68 tools, all read-only. Most wrap one Skylit REST endpoint with the same credit cost; the intelligence tools combine several and are served on their own list (/mcp?toolset=intelligence). 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
Intelligence tools	explain_levels, vol_context, whats_changed, market_brief, flow_context

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 support@skylit.ai.
• Skylit data is market information, not investment advice.

Links

• Docs: www.skylit.ai/docs (MCP overview, quickstart, example prompts)
• Full agent reference (REST, streams, MCP): www.skylit.ai/docs/skill.md
• API keys: app.skylit.ai/developer
• Support: support@skylit.ai
• Security: SECURITY.md
• Legal: Terms, Privacy, API Terms