spx-dealer-gamma
Computes SPX dealer gamma exposure (GEX) from CBOE delayed option quotes and exposes it as an MCP tool for Claude Desktop.
README
spx-dealer-gamma
Computes SPX dealer gamma exposure (GEX) from free CBOE delayed option quotes (~15-minute delay, official open interest and implied volatility — no brokerage market-data entitlement required). Exposed as an MCP tool for Claude Desktop.
Why CBOE delayed quotes
CBOE lists SPX/SPXW natively, so this is a first-party source for OI and IV on the
exact index most dealer-gamma analysis targets — not a proxy via SPY. The public
endpoint (https://cdn.cboe.com/api/global/delayed_quotes/options/_SPX.json) also
returns CBOE's own precomputed per-contract Greeks (delta, gamma, vega, theta),
so the current-spot GEX snapshot uses their greeks directly rather than a
re-derived model.
Method
- Current-spot net GEX:
sign * gamma * open_interest * 100 * spot^2 * 0.01, summed over all contracts with open interest > 0. Calls contribute positively, puts negatively — the standard convention used by most public GEX calculators (dealers modeled as net long gamma via calls / net short via puts). This is a modeling assumption, not directly observable dealer positioning. - Zero-gamma flip level: the current-spot GEX above is a single point. To find where dealer gamma flips sign, this recomputes Black-Scholes gamma for every contract with a valid IV across a scan of hypothetical spot prices (default ±15% band, 121 steps), holding each contract's own quoted IV/strike/expiry fixed, and finds where cumulative signed GEX crosses zero. This does not shift the vol surface with spot (no skew dynamics) — a known simplification shared by most open-source GEX trackers.
- Contracts with
iv <= 0(stale/no recent quote) are excluded from the flip scan but still included in the current-spot snapshot via CBOE's own gamma.
Files
gamma.py— data fetch + calculation, runnable standalone (python gamma.py)server.py— MCP server wrapper exposingspx_dealer_gammaas a tool
Setup
python -m venv .venv
./.venv/Scripts/pip install -r requirements.txt # Windows
# ./.venv/bin/pip install -r requirements.txt # macOS/Linux
Claude Desktop
Add to claude_desktop_config.json:
"spx-dealer-gamma": {
"command": "C:\\path\\to\\spx-dealer-gamma\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\spx-dealer-gamma\\server.py"]
}
Limitations
- 15-minute delayed data, not live.
- Aggregates all listed SPX/SPXW expiries (including LEAPS), not just the front-month/0DTE window some trackers restrict to — net GEX magnitude isn't directly comparable to trackers that scope differently.
- Dealer-side sign convention is an assumption, not observed fact.
- No vol-surface skew shift in the flip scan (see Method above).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.