Option Desk

com.avidquant由 avidquant.com 發布官方發布者v0.3.0更新於 Oct 24, 2026

Option analytics over the SYNTH sample or a permitted chain: Greeks, positioning, payoffs, plots.

已驗證Streamable HTTP可網頁執行金融資料與分析

概覽

AI 產生的概覽

Option Desk 是託管的選擇權分析服務，讓助理彙整選擇權鏈、計算希臘值與持倉分布，並產生報酬圖與行情圖。

可以做什麼
查詢服務狀態、資料模式、來源與授權門檻，並讀取可接受的快照欄位與修復規則。驗證、正規化並匯入使用者提供的選擇權鏈，也可提前刪除已匯入的儀表板。依 SYNTH 樣本或使用者資料彙整選擇權鏈，計算希臘值、伽瑪牆、伽瑪翻轉與最大痛點。繪製行情圖、希臘值階梯圖與結構比較圖，並為指定選擇權結構產生報酬圖。產出含策略紀錄、希臘值單位、情境與成本假設的合併多圖報告，或以使用者資料建立私有互動儀表板。
適用情境
適合讓助理檢視你既有的選擇權鏈、依報酬與希臘值比較多腳結構，或以合成 SYNTH 樣本產生教學式圖表。它著重私有分析與報告，而非即時行情或回測。
執行需求
遠端 streamable HTTP 端點；未宣告任何套件、環境變數或標頭。託管流程涵蓋快照驗證、希臘值、持倉分布與策略圖。SYNTH 樣本不需資料帳號；分析真實標的須自行提供選擇權鏈資料。
安裝前請注意
此服務從不抓取行情資料，結果完全取決於你上傳的選擇權鏈，請確認你擁有該資料的使用權。造市商方向是假設而非實際持倉，結果不是成交、建議或投資意見。匯入的儀表板透過 bearer 連結存取，一小時後過期；資料敏感時可提前刪除。不提供託管回測。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Option Desk，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.avidquant%2Foptiondesk/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "option-desk": {
      "type": "http",
      "url": "https://optiondesk.avidquant.com/mcp"
    }
  }
}

README

Option Desk

Options research with a local dashboard, agent skills, and MCP tools. Import a chain, inspect its Greeks and positioning, compare structures, and keep the results as readable files.

[Checks] [Tests] [Unit coverage gate] [Mutation cases] [Python]

[License] [Ask DeepWiki] [Local skills] [Hosted skills] [Local MCP tools]

[Agent guides] [Last commit]

[MCP Registry] [Option Desk MCP connector, tool definition quality and endpoint health on Glama] [Hosted sample]

Contents

On this page

Guides and wiki

See the desk

The dashboard brings the chain, model assumptions, and research results onto one page. These are captures of the current local dashboard with synthetic teaching inputs. They are not market observations or evidence of trading performance. Capture details distinguish the input scenario from the capture date.

[Structure comparison in the local dashboard, using synthetic inputs]

Dashboard tour

Open an image for its full resolution. The complete gallery includes individual panels and charts. The dashboard guide explains how to read them.

PositioningVolatility
[Synthetic dealer gamma, walls, open interest, and max pain][Synthetic volatility surface, smile, and Greek curves]
Inspect the assumed dealer exposure and chain coverage.Compare strikes and expiries without hiding missing values.
Structure payoffTwo-expiry structures
[Synthetic option structure payoff and legs][Synthetic calendar and diagonal comparison]
Read the legs, breakevens, and limits together.Inspect the valuation assumptions for the surviving leg.
SimulationBacktest
[Simulation panels from synthetic price history][Backtest panels from synthetic price history and modeled premiums]
Read the fan with the convergence diagnostics.Read outcomes with the benchmark and model limitations.
Composite comparisonContract ladder
[Composite scores and their components for synthetic structures][Synthetic contract Greeks and overlaid strategy payoffs]
Inspect the formula and disagreements between models.Compare sensitivities and payoff shapes.

[The dashboard pipeline from input through saved research artifacts]

Get started

Choose one route:

Your starting pointFirst actionContinue with
I want to try it without a data accountRun the supplied sample below.First walkthrough
I use Claude Code or CodexInstall the local tools, then connect the plugin.Agent workflows
I have a CSV or JSON chainImport it with its source and timestamp.Data import
I want a browser-based exampleOpen the hosted sample.Hosted connection

Try the supplied sample

Requirements: Git and Python 3.11 or later. Run these commands on macOS or Linux:

sh
git clone https://github.com/Iman/agent-driven-options-desk-and-skills.gitcd agent-driven-options-desk-and-skillspython3 -m venv .venv. .venv/bin/activatepython -m pip install -e ./engine -e ./shelloptiondesk chain SYNTH --from-file examples/chain-synth.json --accept-data-rights --out-dir artifacts/tutorialoptiondesk greeks --out-dir artifacts/tutorialoptiondesk exposure --out-dir artifacts/tutorialoptiondesk compare --out-dir artifacts/tutorialoptiondesk dashboard --out-dir artifacts/tutorial

Open http://127.0.0.1:8787 on the same computer. Select SYNTH and 2026-10-08. Press Ctrl+C in the terminal to stop the server. The result files remain in artifacts/tutorial.

The supplied sample contains 62 synthetic contracts and a fixed valuation scenario. It needs no external provider after installation. The walkthrough includes Windows activation, expected results, and the next steps. Sample provenance explains the inputs.

Install the full local desk

From a checkout, run:

sh
./install.shoptiondesk doctor

This installs the local tools and skills and attempts MCP registration with supported runtime CLIs it finds. Installation covers paths, flags, Docker, and removal. A plugin installation alone does not install the local calculation engine.

For an existing local provider setup, run the complete demonstration:

sh
./run.sh --symbols SPY

The runner retrieves data, builds the research artifacts, opens a paper position, and serves the dashboard. It writes to ~/TradingDesk/option-desk-demo by default. Use --dry-run to inspect its commands. Read provider setup before enabling Yahoo access.

Ask your agent

Install skills in your product

ProductInstallation choices
Codexnpx, manual copy, shell installer, or plugin.
Claude Codenpx, manual copy, shell installer, or plugin.
ChatGPTIndividual hosted-skill uploads where the account supports Skills, plus a separate MCP app.
Claude chatIndividual hosted-skill ZIPs plus a custom MCP connector.

The installation guide includes single-skill and all-skill commands, user/project scope, ZIP preparation, and connection checks.

After connecting the local tools, ask:

text
Use examples/chain-synth.json, the supplied synthetic teaching sample.I can use this file for private analysis.Save the results under artifacts/tutorial.Show its Greeks and positioning, then compare an iron condor with a straddle.State the source, missing inputs, model assumptions, and degradation first.
What you wantSkillExample
Working toolsdesk-setupCheck why my MCP tools are unavailable.
Contract sensitivitiesoptions-greeksShow delta, gamma, theta, and vega from this chain.
Chain positioningoptions-positioningShow the gamma walls and state the dealer-sign assumption.
Multi-leg structuresoptions-strategyCompare these structures by payoff, loss, and Greeks.
Forward distributionoptions-simulationSimulate the underlying from permitted history and report convergence.
Historical researchoptions-backtestBacktest this structure and explain the benchmark and missing costs.

The local MCP server exposes 12 tools. The hosted service supports a smaller workflow: snapshot validation, Greeks, positioning, and strategy plots. Simulation and backtests remain local workflows. See agent setup and prompts.

Follow a research workflow

StepActionWhat to inspect
1. LoadImport a chainSource, timestamp, expiry, and missing inputs.
2. InspectCalculate Greeks and positioning.Units, skip counts, and dealer-sign assumptions.
3. CompareBuild structuresLegs, breakevens, maximum loss, and spread costs.
4. Explore timeCompare two expiriesNear-expiry valuation and scan limits.
5. Research historySimulate or backtestConvergence, benchmarks, uncertainty, and omitted costs.
6. RecordOpen a paper positionPlan, thesis, later marks, and unavailable quotes.

The dashboard reads saved artifacts. It does not fetch new data when you open the page. Use the same --out-dir for related commands and the dashboard. The results guide explains how to interpret each stage.

Read the documentation

GuidePurpose
User guide homeChoose a task and follow it to a result.
Installation referenceeight install paths for local, plugin, skills-only, hosted, and container use.
Dashboard tourRead the panels and identify missing calculations.
ExamplesCopyable commands and expected results.
TroubleshootingInstallation, provider, import, and chart problems.
FAQCommon questions and interpretation limits.
CapabilitiesFeature and interface catalogue.
Master algorithmOne pseudocode reference for skills, loops, graph routing, prompts, backtests, and paper tests.
ArchitecturePackages, data flow, contracts, current diagrams, and preserved design references.
Preserved project referenceComplete earlier README, with its engineering detail, measurements, and examples.
API inventoryGenerated public function and class reference.
Documentation mapAll guides, policies, and maintenance references.

Where the desk is listed

ListingLinkStatus
Official MCP Registrycom.avidquant/optiondeskPublished 2026-09-11. Remote entry for the hosted endpoint, domain verified.
Smitheryiman-samizadeh/option-deskListed 2026-09-11. Hosted endpoint, 13 tools scanned, TXT record verified.
Glama serverIman/agent-driven-options-desk-and-skillsIndexed from the repository, 12 local tools listed.
Glama connectorcom.avidquant.optiondesk/option-deskHosted endpoint, listed 2026-09-11, health checked by Glama, 13 tools.
Claude Code and Codex marketplacesThis repository: /plugin marketplace add Iman/agent-driven-options-desk-and-skillsLocal plugin option-desk and hosted plugin option-desk-hosted.
Hosted sampleoptiondesk.avidquant.com, MCP at /mcpSynthetic SYNTH data, no account needed.
LinkedIn articleI built an options desk an agent can drivePublished 2026-09-10.
dev.todev.to/imansamizadehRepost of the article, canonical link to LinkedIn, publishes after the first week.

Directory listings describe the hosted endpoint or the repository as they were on the date shown. The listing pages are maintained on each directory, not in this repository.

Development

Testing and coverage covers happy and failure paths, BDD scenarios, integration checks, and the 80% unit line-coverage gate per package.

Run from the repository root with the development dependencies installed. See Development for environment setup and screenshot capture.

sh
python -m pytest engine/tests -q    # 355 testspython -m pytest shell/tests -q     # 574 testspython -m pytest agent/tests -q     # 161 testspython -m pytest -q                # 1090 tests

These are collection counts, not a claim that this documentation edit ran every test. The workflow badge links to the actual CI result.

sh
python3 scripts/refresh.py --no-indexpython3 scripts/mutate.py --list

Ten stages in a full run rebuild generated documents and packages, check recorded evidence, and run the suites and repository rules. The mutation harness defines ninety-nine mutations. Use its output to distinguish detected changes, survivors, and skipped cases.

Eight schemas under shell/src/optiondesk/contracts/ define the artifact interface: 8 schemas + validator. See the architecture guide for their roles.

Recorded historical example

The evidence record pins an earlier chain measurement to 2026-08-30T14:12:17+00:00. It records 607 contracts, spot, listed expiries and 595 solved, 12 refused as unidentified. These are historical evidence strings, not counts for the sample or the current screenshots. The recorder retains them here for its existing documentation checks.

Contribute · Backlog · Changelog · Security

Licensing

The repository uses PolyForm Noncommercial 1.0.0. It is source available and free for noncommercial use. Commercial use requires a separate written agreement. See LICENSES.md. The software license does not grant rights to provider data.

Research software. No order placement. Model results are not fills, recommendations, or investment advice. Read the disclaimer, privacy policy, and third-party notices.

來源：README.md，提交 c802f0e

工具

13

option_desk_status

Check the Option Desk data mode, source, refresh time, and public licence gate before requesting figures. No live feed or hosted backtest tool exists, even with uploaded history. Do not offer hosted backtests.

無需輸入參數。

option_snapshot_schema

Return the accepted CSV and JSON option-chain fields, safe repair rules, size limits, data-rights confirmation, and retention policy.

無需輸入參數。

option_chain_snapshot

Summarize SYNTH or analyze a user-supplied option chain for private analysis. This service never fetches market data.

輸入參數rateexpirysymboldata_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_positioning

Return gamma walls, gamma flip, and max pain from SYNTH or a user-supplied chain. Dealer signs are an assumption, not observed positions.

輸入參數rateexpirysymboldata_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_plots

Render opaque PNG plots in the conversation. The SYNTH sample offers the market plot (dealer gamma exposure, open interest, volume and the smile by strike), the Greek ladder, and the structure comparison. Each is computed from the sample's own engine artifacts; there is no simulation or backtest for SYNTH because the hosted service has no price history.

輸入參數plotrateexpirysymboldata_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_strategy_plot

Show an option-strategy payoff as an opaque PNG in the conversation. Any structure in the engine playbook can be built on the SYNTH sample chain. A market ticker requires user-supplied chain data. Do not start a localhost dashboard.

輸入參數rateexpirysymbolstrategydata_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_report_plots

Return the market map, Greek ladder, strategy comparison and up to three requested payoff charts in ONE widget. Prefer this tool for multi-chart reports instead of parallel individual plot calls. Includes strategy_records, Greek units, scenarios and cost assumptions. Use those records for tables; never invent currency or a multiplier. Uses SYNTH or a user-supplied chain; never fetches live data.

輸入參數rateexpirysymbolstrategiesdata_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_private_dashboard

Create a private interactive dashboard from user-supplied data. The bearer URL and all derived artifacts expire after one hour.

輸入參數rateexpirysymbol必填data_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmedretention_confirmed

option_validate_snapshot

Validate and safely normalize a user-supplied option-chain snapshot. Return corrections and a summary. Delete all temporary files before the response.

輸入參數rateexpirysymbol必填data_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_import_snapshot

Import user-supplied option-chain data into a bearer-private interactive dashboard. Delete the artifacts after one hour.

輸入參數rateexpirysymbol必填data_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmedretention_confirmed

option_plots_from_snapshot

Create opaque market and Greek PNG images from a user-supplied snapshot. Stamp source, capture time, expiry, and warnings on every image. Delete temporary files before the response.

輸入參數rateexpirysymbol必填data_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_strategy_from_snapshot

Build one option structure from a user-supplied chain and return its opaque payoff PNG with permanent source and risk warnings.

輸入參數rateexpirysymbol必填strategydata_sourcesource_datasource_textsource_formatdividend_yieldrights_confirmed

option_delete_snapshot

Delete one short-lived imported dashboard before its automatic one-hour expiry.

輸入參數token必填

版本歷史

1
  1. v0.3.0最新Sep 16, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。