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.
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
- Create and activate a virtual environment.
- Install the project in editable mode with dev dependencies:
pip install -e '.[dev]' - Set
BIBLE_SOURCE_DBto a SQLite database that contains the sourceversestable. The importer expects at leastbook,chapter,verse, andtext, and it can also read optionaltranslation. - Fetch theographic metadata snapshot:
bible-mcp fetch-theographic - Sync fetched metadata into the app DB:
bible-mcp sync-theographic - Run indexing (offline; does not fetch metadata remotely):
bible-mcp index - Start the MCP server:
bible-mcp serve
Commands
bible-mcp fetch-theographicdownloads the configured theographic snapshot into the local vendor directory.bible-mcp sync-theographicnormalizes the fetched snapshot and syncs metadata rows into the app database.bible-mcp indeximports 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 servevalidates 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 doctorvalidates the source database and the generated runtime artifacts without starting the server.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.