Corpus

world.wheelofheaven.mcp由 mcp.wheelofheaven.world 發布官方發布者v0.1.1更新於 Oct 24, 2026

Read-only Wheel of Heaven corpus: myth search, primary texts, datasets, typed graph. CC0.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取知識與記憶

概覽

AI 產生的概覽

唯讀存取 Wheel of Heaven 語料庫,讓助理檢索神話與經典文本、查閱來源,並查詢具型別的內容圖譜。

可以做什麼
檢索由維基條目、時間軸章節、文庫文本、文章與新聞組成的語料庫,並以 Markdown 形式取得單一條目,附帶主張中繼資料、引用與九種語言版本。以附穩定引用編號的段落形式取得數位化原始文獻的章節。查閱書目記錄與比較神話資料集的資料列。查詢內容圖譜中某個節點的一跳鄰域。讀取專案自身的詮釋框架、編輯方法與術語表條目。
適用情境
適合助理研究比較神話學、古代原始文獻,或 Wheel of Heaven 專案以 Raël 教義為中心的詮釋,且需要區分有來源的事實與專案自身解讀的場合。
執行需求
遠端 streamable HTTP 端點,或透過 npm 套件以 npx 在本機執行。未宣告需要身分驗證、API 金鑰或環境變數。
安裝前請注意
詮釋層呈現的是專案自身以 Raël 教義為中心的立場,而非主流共識,應將其視為一種觀點並核對主張類型。內容為唯讀,但每次工具呼叫都會請求上游 API,查詢內容會傳送給第三方。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Corpus,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/world.wheelofheaven.mcp%2Fcorpus/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": {
    "corpus": {
      "type": "http",
      "url": "https://mcp.wheelofheaven.world/mcp"
    }
  }
}

README

mcp.wheelofheaven.world

Read-only MCP server for the Wheel of Heaven corpus. It wraps the static JSON API at api.wheelofheaven.world so AI agents can search and retrieve the corpus with full epistemic metadata (claim types, editorial passes, citations).

Design rationale and tool-surface spec: .claude/plans/strategy-mcp-server.md in the org .claude repo.

Endpoints

  • /mcp — Streamable HTTP (canonical)
  • /sse — legacy SSE transport
  • / — server info (JSON)

Install

Remote (recommended — nothing to run locally):

bash
claude mcp add --transport http wheel-of-heaven https://mcp.wheelofheaven.world/mcp

Local stdio via npm (@wheelofheaven/mcp):

bash
npx -y @wheelofheaven/mcp

Registry listing: world.wheelofheaven.mcp/corpus in the official MCP registry.

Tools

Fact layer — source-grounded data, no interpretation applied:

ToolPurpose
search_corpusFuzzy full-text search over wiki, timeline, library books, articles, and news (~290 documents; token-AND with OR fallback)
get_entryOne wiki/timeline/articles/news entry as markdown with claim_type, editorial_pass, typed related-content edges, and canonical citation URLs; 9-language support via lang
get_passageA chapter of a digitized primary source text as numbered paragraphs with stable reference IDs (e.g. GEN-1:26); ref filters to one verse
get_sourceBibliography lookup by stable ID or search — every record carries the source-program classification (family, stance, relation), critical sources included
compare_traditionsRows from the comparative datasets: flood-myths, divine-council-index, theomachy-crossrefs, world-ages, prophets-and-religions
query_graphTyped 1-hop ego network of any corpus node (see_also, in_body, cites_source, same_tradition, same_age, comparison_of)

Interpretation layer — explicitly the project's own reading, labeled as such:

ToolPurpose
get_interpretationThe Wheel of Heaven framework's reading of a topic (curated context documents, or the closest wiki entry), always carrying an interpretation-layer notice
get_methodThe editorial methodology: claim-type taxonomy, six-source rule, editorial passes — how to weigh everything else

Meta:

ToolPurpose
get_glossary_termCore terminology with renderings in all 9 site languages (exact-id match first)

Resources: the six /v1/context/* narrative documents (woh://context/{overview,hypothesis,terminology,timeline,sources,method}) plus woh://llms.txt.

Development

bash
npm installnpm run dev        # wrangler dev on :8787npm run typechecknpm run deploy     # wrangler deploy (needs Cloudflare auth)

The server is stateless over the upstream API: every tool call fetches api.wheelofheaven.world/v1/…, with the ~600 KB search corpus cached in-memory per isolate for one hour (matching the API's edge-cache TTL).

Architecture

  • Cloudflare Workers + agents SDK (McpAgent Durable Object)
  • src/server.ts — transport-agnostic tool registration (reused by the future npm stdio build)
  • src/api.ts — /v1/ client + search-corpus cache
  • src/html.ts — deterministic body_html → markdown conversion

Related repositories

License

CC0-1.0 — like the corpus itself.

來源:README.md,提交 97a8fb9

工具

9

search_corpus

Full-text search over the Wheel of Heaven corpus: wiki encyclopedia entries, the precessional-ages timeline, digitized library source texts (Genesis, Atrahasis, Gilgamesh, Enuma Elish, the Raëlian books, and ~120 more), research articles, and newsroom dispatches. Returns ranked matches with slugs and URLs; fetch full content with get_entry (wiki/timeline/articles/news). Every result is CC0 and citable by its html URL.

輸入參數limitquery必填section

get_entry

Fetch one Wheel of Heaven entry — an encyclopedia (wiki) entry, a precessional-age timeline chapter, a research article, or a newsroom dispatch — as markdown with its epistemic metadata: claim_type (direct = explicit in a primary source and mainstream-uncontroversial; framework = explicit in the project's canon but not mainstream-endorsed; inferred = reasonable reading; speculative = interpretive synthesis), editorial_pass, references, typed related-content edges, and canonical citation URLs. Long bodies are truncated unless full_body=true.

輸入參數langslug必填section必填full_body

get_passage

Fetch a chapter of a digitized primary source text from the Wheel of Heaven library (Genesis, Atrahasis, Epic of Gilgamesh, Enuma Elish, the Book of Enoch, the Raëlian books, and ~120 more) as numbered paragraphs with stable reference IDs (e.g. GEN-1:26). Optionally filter to one verse/paragraph with ref. This is the primary-source tool: it returns the text itself, not interpretation. Find book slugs with search_corpus (section=library). English editions in v1.

輸入參數refbook必填chapter必填

get_source

Look up the Wheel of Heaven bibliography (source program). Pass id for one full source record (description, author, publish date, licensing, link); pass query to search records by title/family/stance. Every record carries the source-program classification: source_family, stance (supportive/neutral/critical/mixed), and relation_to_wheel — the bibliography deliberately includes critical and skeptical sources.

輸入參數idlimitquery

compare_traditions

Return rows from one of the Wheel of Heaven comparative-mythology datasets: myth-index (75 motif attestations across 9 families with Thompson Motif-Index cross-references — the spine table), aarne-1910-tale-types (the structured Aarne 1910 folktale-type catalogue, 603 rows), grimm-khm-index (all 211 Grimm KHM tales with ATU types and Aarne-1910 joins), antediluvian-chronologies (SKL kings, Berossos, and Genesis 5/11 patriarchs in MT/SP/LXX parallel), flood-myths (survivor, decreeing power, warner, vessel, birds, landing place across 11 traditions), divine-council-index, theomachy-crossrefs (divine-combat motifs), world-ages (precessional ages), or prophets-and-religions. Source-grounded comparison tables with links to the digitized texts — no interpretation applied. CC0; also on Hugging Face and Kaggle.

輸入參數filterdataset必填

query_graph

Query the typed Wheel of Heaven content graph: the 1-hop ego network of any corpus node, with typed edges (see_also, in_body, cites_source, same_tradition, same_age, comparison_of) in both directions plus resolved neighbor titles/URLs. Useful for finding everything connected to a concept, or how two entries relate.

輸入參數slug必填section必填edge_type

get_interpretation

Return the Wheel of Heaven interpretive framework's reading of a topic — explicitly the project's own Raëlian-canon-centred position, NOT mainstream consensus. Accepts a framework topic (overview, hypothesis, terminology, timeline, sources, method) for the curated narrative documents, or any other term to get the framework reading from the closest wiki entry. Use fact-layer tools (get_passage, compare_traditions) for source-grounded data without this framing.

輸入參數topic必填

get_method

Return the Wheel of Heaven editorial methodology: the claim_type taxonomy (direct/framework/inferred/speculative), the six-source rule (every new entry cites a Raëlian, ancient-primary, scholarly, scientific, comparative-tradition, AND critical source), editorial passes, and translation policy. Call this to understand how to weigh everything else this server returns.

無需輸入參數。

get_glossary_term

Look up a core Wheel of Heaven term (Elohim, Yahweh, precession, World Ages, …) in the project glossary, returning its definition and renderings in all 9 site languages. Pass no term to list all glossary terms.

輸入參數term

版本歷史

1
  1. v0.1.1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。