Bible MCP

Bible MCP

Enables local-first semantic search and retrieval of Korean Bible verses using FAISS embeddings and full-text indexes. Supports exploration of biblical entities including people, places, and events with Korean-to-English query handling.

Category
访问服务器

README

bible-mcp

bible-mcp is a local-first Korean Bible MCP server. It imports verses from a source SQLite database, builds passage chunks and search indexes, and serves those indexes through an MCP server.

V2 metadata slice: metadata is fetched and synced explicitly before indexing. bible-mcp index now depends on metadata that was already synced into the app DB.

V2 entity search defaults to people for backwards compatibility; to search bundled place or event metadata, call search_entities with an explicit entity_type such as places or events.

Client-Side Entity Retry

Bible MCP assumes entity rewrite happens in the MCP client when Korean input needs English metadata retries. The server exposes route_entity_query, but the retry loop stays in the client layer.

See docs/integrations/llm-entity-rewrite.md for the integration contract and retry flow.

Setup

  1. Create and activate a virtual environment.
  2. Install the project in editable mode with dev dependencies: pip install -e '.[dev]'
  3. Set BIBLE_SOURCE_DB to a SQLite database that contains the source verses table. The importer expects at least book, chapter, verse, and text, and it can also read optional translation.
  4. Fetch theographic metadata snapshot: bible-mcp fetch-theographic
  5. Sync fetched metadata into the app DB: bible-mcp sync-theographic
  6. Run indexing (offline; does not fetch metadata remotely): bible-mcp index
  7. Start the MCP server: bible-mcp serve

Commands

  • bible-mcp fetch-theographic downloads the configured theographic snapshot into the local vendor directory.
  • bible-mcp sync-theographic normalizes the fetched snapshot and syncs metadata rows into the app database.
  • bible-mcp index imports source verses, requires already-synced metadata, rebuilds chunks and FTS indexes, and writes FAISS embeddings. It is offline and does not fetch metadata remotely.
  • bible-mcp serve validates the app database and FAISS artifacts, then starts the MCP server. When optional metadata tables are available it also exposes entity search and entity relation tools.
  • bible-mcp doctor validates the source database and the generated runtime artifacts without starting the server.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选