Skip to main content
MCP server CX Codex

Option Desk — Claude Code MCP server for options analysis

Analyze option chains with Greeks, positioning views, strategy comparisons, and payoff charts. A local dashboard also lets you inspect a supplied synthetic sample.

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http optiondesk https://optiondesk.avidquant.com/mcp
Open on GitHub

What Option Desk does

Option Desk gives an agent tools for examining option chains, reviewing Greeks and positioning, and comparing structures by their modeled payoffs. Research results can be kept as readable files. A local dashboard brings the chain, assumptions, and findings together.

The supplied sample runs without an external data provider after installation, but it requires Git and Python 3.11 or later. Its contracts and valuation scenario are synthetic, so the charts are not market observations. Keep that distinction in mind when interpreting the sample.

What it helps with

  • inspect Greeks across an option chain
  • compare positioning and open interest
  • view strategy legs and breakeven levels
  • plot modeled structure payoffs

Example prompts for the agent

  • Review the Greeks and positioning in this option chain.
  • Compare these structures by their modeled payoff and plot the results.
  • Show the synthetic sample in the local dashboard.

How to install Option Desk

Platform CLI: remote server

claude mcp add --transport http optiondesk https://optiondesk.avidquant.com/mcp

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Option Desk

How do I install Option Desk in Claude Code?

Run both commands: claude mcp add --transport http optiondesk https://optiondesk.avidquant.com/mcp, then claude mcp add --transport http option-desk https://optiondesk.avidquant.com/mcp.

What does Option Desk do?

It provides tools for analyzing option chains, Greeks, and positioning, and for comparing structures and their modeled payoffs.

Does the sample need an external data provider?

No. After installation, the supplied sample runs without one. The sample requires Git and Python 3.11 or later.

Similar MCP servers

MCP servers catalog →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor