Caelune
A local-first Windows desktop app and read-only MCP server for searching private Markdown, PDF, and Tika-backed knowledge bases.
Усильте агента
Собственная команда издателя. Не эндпоинт PlugMCP.
Host a copy with our keys and logs.
mcpb https://github.com/EllisMorrow/OmniClip-RAG/releases/download/v0.4.13/omniclip-rag-mcp-win-x64-v0.4.13.mcpbУ Claude Code нет ссылки для установки локальной команды. Скопируйте команду ниже и выполните её в терминале.
claude mcp add io.github.ellismorrow-omniclip-rag-mcp -- mcpb https://github.com/EllisMorrow/OmniClip-RAG/releases/download/v0.4.13/omniclip-rag-mcp-win-x64-v0.4.13.mcpbВыполните в терминале.
{ "mcpServers": { "io.github.ellismorrow-omniclip-rag-mcp": { "command": "mcpb", "args": [ "https://github.com/EllisMorrow/OmniClip-RAG/releases/download/v0.4.13/omniclip-rag-mcp-win-x64-v0.4.13.mcpb" ] } }}claude_desktop_config.json
Удалённый URL или команда на вашем компьютере? Чем различаются два способа установки
Запустить на PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
ЗапускCaelune builds searchable indexes from knowledge you already keep on your own computer. It combines exact-text retrieval, structural signals, semantic vector search, optional reranking, and source-aware context assembly.
The desktop app manages data roots, Runtime components, models, knowledge-base builds, live watch, queries, and result review. The optional MCP server exposes the same retrieval core to MCP-capable AI clients through two read-only tools.
The Query Console keeps input, scope, retrieval settings, and live query state together. Results and Details uses a separate page for source-labelled hits, snippet review, full-context selection, and page filtering.
Open the latest release and choose the package that matches your use case:
The MCP package does not build or modify knowledge bases. Build the index with the Windows desktop app first.
BAAI/bge-m3, and optional BAAI/bge-reranker-v2-m3.Caelune is local-first, not a promise that every possible workflow is permanently offline.
Keep backups of important source material and review retrieved context before using it in high-stakes work.
WIN-EXE.Caelune.exe.Detailed instructions: Getting Started.
The Runtime and models are external sidecars so healthy components can be reused across application versions. See Runtime and Models.
flowchart LR
A["Markdown / PDF / Tika sources"] --> B["Local parsing and indexes"]
B --> C["FTS5 lexical recall"]
B --> D["LanceDB semantic recall"]
C --> E["Fusion and filters"]
D --> E
E --> F["Optional reranking"]
F --> G["Results and context pack"]
G --> H["Clipboard or read-only MCP"]
stdio configuration, or use the Registry/MCPB package.Caelune-MCP.exe.omniclip.status to inspect readiness and active retrieval modeomniclip.search to retrieve source-labelled resultsSome clients do not accept local stdio servers directly and may require a local proxy. See the MCP Integration Wiki and MCP_SETUP.md.
# Desktop GUI
.\scripts\run_gui.ps1
# CLI status and query
.\scripts\run.ps1 status
.\scripts\run.ps1 query "your question"
# Build Windows packages
.\scripts\build_exe.ps1
# MCP self-check from source
python launcher_mcp.py --mcp-selfcheck
Developer orientation and architecture links live in Development and Architecture.
Caelune is released under the MIT License. It relies on open-source projects including PySide6, SQLite, LanceDB, Apache Arrow, PyTorch, sentence-transformers, Transformers, BGE models, PyPDF, Apache Tika, Eclipse Temurin, watchdog, PyInstaller, and the Model Context Protocol SDK.
See THIRD_PARTY_NOTICES.md for the repository-level legal and distribution notices.
Caelune and its retrieval results are provided without warranty. Verify important results, maintain backups, and do not use retrieved context or downstream AI output as the sole basis for medical, legal, financial, safety-critical, or other high-stakes decisions.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
{ "mcpServers": { "io.github.ellismorrow-omniclip-rag-mcp": { "command": "mcpb", "args": [ "https://github.com/EllisMorrow/OmniClip-RAG/releases/download/v0.4.13/omniclip-rag-mcp-win-x64-v0.4.13.mcpb" ] } }}Инструменты
Списка инструментов пока нет. У удалённых серверов он появляется после первой проверки состояния.
FAQ
Скопируйте на этой странице конфигурацию stdio для Cursor, Claude Desktop, Claude Code или VS Code. Она использует установку издателя, а не прокси PlugMCP.
В этой записи не указано обязательных переменных окружения.
OmniClip RAG работает локально через stdio.
Последняя проверка: 2026-11-09. Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.