mcp.wheelofheaven.world

MCP serverSearch

This integration gives your AI read-only access to the Wheel of Heaven corpus, a freely licensed (CC0) collection of myths, primary texts, datasets, and a typed graph. Once added, your AI can search the corpus and use its source material when answering your questions.

Use mcp.wheelofheaven.world in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add mcp.wheelofheaven.world and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use mcp.wheelofheaven.world to search corpus

Details

Available today. Use it from your connected AI after setup.

After adding it, ask your AI about a myth or topic from Wheel of Heaven and let it search the corpus for the answer.

mcp.wheelofheaven.worldStart free

What your AI can do with it

  • Search the Wheel of Heaven corpus for myths
  • Read and quote primary texts from the corpus
  • Pull information from the corpus's datasets
  • Follow connections between entries in the corpus's typed graph
  • Answer questions from the corpus without altering it, since access is read-only

Install mcp.wheelofheaven.world

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user mcp-wheelofheaven-world 'https://mcp.wheelofheaven.world/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://mcp.wheelofheaven.world/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-wheelofheaven-world&config=eyJ1cmwiOiJodHRwczovL21jcC53aGVlbG9maGVhdmVuLndvcmxkL21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://mcp.wheelofheaven.world/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add mcp-wheelofheaven-world --url 'https://mcp.wheelofheaven.world/mcp'

    Run it once, then sign in with codex mcp login mcp-wheelofheaven-world if the server asks for an account.

From the project's README

As published by wheelofheaven/mcp.wheelofheaven.world in README.md.

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):

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

Local stdio via npm (@wheelofheaven/mcp):

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

npm install
npm run dev        # wrangler dev on :8787
npm run typecheck
npm 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.

Tools it offers (9)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • search_corpus
  • get_entry
  • get_passage
  • get_source
  • compare_traditions
  • query_graph
  • get_interpretation
  • get_method
  • get_glossary_term

Signals

Last commit
Aug 2026
Advanced
Delivery
corpus MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
world-wheelofheaven-mcp-corpus
Source
github.com/wheelofheaven/mcp.wheelofheaven.world
Hosted endpoint
https://mcp.wheelofheaven.world/mcp