Archive MCP connector
Connect this library to ChatGPT, Claude, Cursor, VS Code, Gemini CLI, Zed, JetBrains, OpenCode, and other MCP clients.
MCP (Model Context Protocol) lets an AI client call our archive search tools directly. You keep your chosen model’s reasoning; the server supplies the same historical publication index used on this site. The connector itself does not generate answers — it only returns source excerpts for the model to use.
Connector URL
Use this URL in any client that supports remote or Streamable HTTP MCP. It is a machine endpoint, not a web page.
https://jwlib.thewt.org/mcp
https://jwlib.thewt.org/sse.
Health check: /mcp-health.
Set up in ChatGPT Plus
Based on OpenAI’s Developer mode and MCP apps help docs. UI labels can shift slightly; use the web app (not only mobile).
- Use an eligible plan. Developer mode / custom MCP connectors are available on paid plans including Plus, Pro, Business, Enterprise, and Education (web).
- Enable Developer mode. In ChatGPT open Settings → Security and login and turn on Developer mode. On some accounts the toggle is under Settings → Apps → Advanced settings.
- Create a custom MCP app. Go to chatgpt.com/plugins (or Settings → Apps / Connectors), click the + button, and create a developer-mode app. The + option for custom MCP apps appears only after Developer mode is on.
-
Enter connection details.
Name: e.g. WT Library Archive.
MCP server URL:
https://jwlib.thewt.org/mcp. Authentication: No Authentication. Protocol: streaming HTTP / Streamable HTTP if asked. -
Review discovered tools.
After connect, ChatGPT should list tools such as
search_articles,get_chunk,get_chunk_context, andget_article. Leave them enabled. You can refresh the app later if tools change. - Use it in a chat. Open a new conversation, choose Developer mode from the composer / tools menu, and select this app. Ask archive questions explicitly, e.g. “Use the WT Library Archive tools to find when publications first stated that Christ’s presence began in 1914 instead of 1874.”
What you get
-
search_articlesHybrid search over 1879–1980 publications (semantic + keyword + exact phrases). Supports year filters and oldest-first sorting. -
get_chunkFetch one indexed excerpt by chunk id, with offsets and neighbor ids. -
get_chunk_contextExpand text before/after a hit without loading the whole article — useful to verify quotes. -
get_articlePaginated plain-text fetch for one article when broader reading is needed. -
list_bible_translationsLists the available Russian, Ukrainian, and English Bible translations and their coverage. -
get_bible_passageReturns exact Bible text in a selected translation, a reader link, and ranked cross-reference candidates. -
search_bibleLiteral wording search in a selected translation; useful when the reference is unknown. -
find_articles_citing_bible_passageFinds archive articles that explicitly cite a requested verse or range.
Compared with the on-site AI Assistant: ChatGPT can run longer tool chains, compare more eras in one session, and apply its own reasoning style — while still grounding claims in this archive.
Other clients
The same /mcp URL automatically supports both classic MCP clients and the newer
MCP 2026 negotiation. Clients limited to the older HTTP+SSE transport can use /sse.
Claude Code
claude mcp add --transport http jwlib https://jwlib.thewt.org/mcp
Codex
codex mcp add jwlib --url https://jwlib.thewt.org/mcp
Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"jwlib": { "url": "https://jwlib.thewt.org/mcp" }
}
}
VS Code / GitHub Copilot (.vscode/mcp.json)
{
"servers": {
"jwlib": { "type": "http", "url": "https://jwlib.thewt.org/mcp" }
}
}
Gemini CLI (settings.json)
{
"mcpServers": {
"jwlib": { "httpUrl": "https://jwlib.thewt.org/mcp" }
}
}
Zed / JetBrains / OpenCode
Add a remote server with URL https://jwlib.thewt.org/mcp.
In JetBrains choose streamable-http. In OpenCode set type: "remote",
oauth: false, and optionally protocol: "auto" for MCP 2026.
Recommended workflow: search_articles → get_chunk_context on promising hits → dig into one article with article_id or get_article only when needed.
Notes
- Tools are read-only (
readOnlyHint). They cannot modify the archive. - Rate limiting applies per IP. Avoid bulk scraping; use focused queries.
- Returned text is historical source material — treat it as untrusted content for the model.
- Bible cross-references are navigation candidates, not evidence until their exact text is retrieved.
- The model should identify the Bible translation and distinguish the passage itself from a publication’s interpretation or application.
- If a client cannot connect, confirm it is using remote Streamable HTTP with the
/mcpURL, or legacy SSE with/sse, and that health returnsok.