ragwatcher
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.
ragwatcher
Local RAG over a directory. Incremental. Served as MCP tool + CLI.
Zero-config default (drops into
~/notes, works).Offline, CPU-only baseline (FastEmbed ONNX). GPU / API models opt-in.
CLI is a peer to the MCP server, not a wrapper.
Install
uv tool install ragwatcher
# or
pipx install ragwatcherOptional extras: [lance] (LanceDB store), [pdf-pro] (pymupdf), [remote] (qdrant/openai/cohere).
Related MCP server: Corpus-KB
Usage
ragwatcher serve ~/notes # MCP server (stdio)
ragwatcher index ~/notes # one-shot sync
ragwatcher query ~/notes "what is X" # one-shot query
ragwatcher stats ~/notes # index summary
ragwatcher doctor ~/notes # health check
ragwatcher purge ~/notes --yes # wipe .rag_index/Every data-producing command supports --json for scripting.
Configuration
Precedence (low → high): defaults → $XDG_CONFIG_HOME/ragwatcher/config.toml → <DIR>/.ragwatcher.toml → RAGWATCHER_* env vars → CLI flags.
See SPEC.md § 5 for the full schema.
Development
uv sync --extra dev
uv run pytest -q --ignore=tests/integration
uv run ruff check src tests
uv run mypy srcIntegration tests (real embed model, ~3s):
uv run pytest tests/integration -m slowLicense
MIT
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
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
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.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Related MCP Servers
- AlicenseAqualityDmaintenanceLocal-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.38 npmMIT
- AlicenseBqualityBmaintenanceLocal end-to-end RAG system for agentic code editors, exposing retrieval-augmented generation via MCP to any compatible client.331MIT

devitway-rag-starterofficial
FlicenseNot gradedqualityDmaintenanceMinimal local RAG stack with an MCP server that provides document search for any agent.1-- AlicenseNot gradedqualityBmaintenanceMCP server for local RAG over personal notes, PDFs, and documents, enabling plain-English querying and hybrid search with multi-hop context expansion.MIT