hartsofflinetoolkit
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
HartsOfflineToolkit (Windows 10 / 11 Edition)
Official Website: https://hartsofflinetoolkit.com
Linux Edition: https://github.com/golfgolfgolf200/hartsofflinetoolkit-linux
HartsOfflineToolkit for Windows is an air-gapped, CPU-only hybrid semantic search engine and Model Context Protocol (MCP) server built natively for Windows 10 and Windows 11 (x86_64) — no WSL, Docker, or GPU required.
It combines Google EmbeddingGemma 2 (google/embeddinggemma-2, truncated via Matryoshka Representation Learning to 256 dimensions) with BM25 lexical scoring and Reciprocal Rank Fusion (RRF) inside a local LanceDB vector store, governed by Windows CPU core affinity (cpu_affinity), BELOW_NORMAL_PRIORITY_CLASS / IDLE_PRIORITY_CLASS scheduling, and IOPRIO_VERYLOW background disk I/O.
Key Capabilities
100% Air-Gapped Runtime (
HF_HUB_OFFLINE=1): Zero outbound telemetry or network calls after one-timecli.py initsetup.Native Windows Hardware Governor: Pins process execution to designated CPU cores (
CPU_AFFINITY_CORES=0,1,2), caps PyTorch/OMP/MKL worker threads, and setsBELOW_NORMAL_PRIORITY_CLASS+IOPRIO_VERYLOWso foreground apps, video calls, and games never stutter.Incremental SHA-256 Delta Indexing: Skips unchanged files in milliseconds, atomically replaces modified files, and purges deleted documents.
Table-Preserving Overlapping Chunking: Extracts PDF tables via
pdfplumberas intact Markdown grids and splits long.pdf,.md, and.txtfiles into overlapping word windows (CHUNK_WORDS=400,CHUNK_OVERLAP_WORDS=50).Hardened
stdioMCP Server (mcp_server.py): Plugs directly into VS Code Copilot, Claude Desktop, Cursor, or local MCP hosts with root-jailed indexing (./data/raw), optionalMCP_READ_ONLY=1lock, and warm in-RAM sub-50ms search.
Related MCP server: docs-search-mcp
Quick Start (PowerShell)
# 1. Clone the Windows repository
git clone https://github.com/golfgolfgolf200/hartsofflinetoolkit-linux-windows.git
cd hartsofflinetoolkit-windows
# 2. Verify repository file hashes against SHA256SUMS
powershell -ExecutionPolicy Bypass -File .\verify.ps1
# 3. Create .venv, install CPU-only PyTorch, download EmbeddingGemma 2, and lock weights
powershell -ExecutionPolicy Bypass -File .\setup.ps1
# 4. Activate the virtual environment
.\.venv\Scripts\Activate.ps1Daily CLI Commands
# Check CPU core affinity, RAM usage, and LanceDB status
python cli.py status
# Incrementally index PDFs, Markdown, and text files in .\data\raw
python cli.py index
# Hybrid semantic + exact keyword search
python cli.py search "30-day cancellation terms" --limit 5
# Machine-readable JSON output for PowerShell pipelines
python cli.py search "REF-99482-TX" --json
# Zero-cold-start interactive REPL mode (keeps model warm in RAM)
python cli.py interactiveWindows MCP Client Configuration (mcp.json / claude_desktop_config.json)
{
"mcpServers": {
"hartsofflinetoolkit": {
"command": "C:\\Users\\<username>\\projects\\hartsofflinetoolkit-windows\\.venv\\Scripts\\python.exe",
"args": [
"C:\\Users\\<username>\\projects\\hartsofflinetoolkit-windows\\mcp_server.py"
]
}
}
}Model Attribution & Licensing
Powered by Google EmbeddingGemma 2 (google/embeddinggemma-2), governed by the Gemma Terms of Use. Toolkit source code is licensed under LICENSE.md
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP server for search and retrieval over a local LanceDB database
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.95,381 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to search and read a folder of Markdown/text documents via a read-only MCP server with hybrid BM25 and local embedding search, treating the calling model as untrusted.13 npmMIT
- AlicenseAqualityBmaintenanceEnables developers to index and search their own local PDF, DOCX, Markdown, and text documents from an MCP client or terminal, combining semantic similarity with keyword matching for exact technical terms. Everything runs on the user's machine with no API key, Docker, or external database, so private documents stay private and work offline after the initial model download.9MIT
- AlicenseAqualityBmaintenanceSemantic code search for any MCP client: indexes local folders of code and docs and answers plain-language or code queries with matching passages, file paths, line ranges and scores. Embedding runs on the local CPU with the Motherlode code-search encoder, so no file content leaves the machine; the encoder downloads once from Hugging Face. Install: npx -y blackwindow-weave-mcp.487 npm1Business Source 1.1