Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gemini-KG-RAG-coding-expert Find non-deprecated Gemini API methods for generating content with code examples."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Graph-RAG source toolkit for indexing Gemini documentation and application code into an interpretable, named-dimension knowledge graph with hybrid retrieval and an MCP interface.
Status: The v0.1 implementation and 65-test suite are complete. This source release intentionally excludes the generated kg_rag.db and the author's source corpus; rebuild the database from content you are permitted to index before using the retrieval CLI or MCP server.
python -m venv .venv
. .venv/bin/activate
python -m pip install -e ".[retrieval,test]"
python -m pytest -qThe final command should report 65 passed.
When Termux already provides NumPy and pytest as native system packages, reuse them instead of building NumPy from its source distribution:
python -m venv --system-site-packages .venv
. .venv/bin/activate
python -m pip install --no-deps -e ".[retrieval,test]"
python -m pytest -qThis sequence also reports 65 passed. --no-deps is appropriate only when the
listed extras are already available from the system Python.
Related MCP server: linked-docs
The repository does not redistribute the Gemini SDK documentation or the private application corpora used by the author. Build a source-specific database from your own Markdown files, score its named dimensions, and then start the MCP server:
python scripts/ingest_markdown.py --paths path/to/your/docs
python scripts/score_heuristic.py
python -m pip install -e ".[retrieval,mcp]"
python -m src.serverscripts/ingest_typescript.py is an optional corpus adapter whose default roots
describe the author's workstation. Edit or adapt CLI_ROOT and MVP_ROOTS before
using it with another checkout. The repo-local .mcp.json uses the checkout as its
working directory; install the retrieval and mcp extras in the Python environment
used by your MCP client.
SQLite single-file store with 10 node types and 11 edge types. Each node carries a 50-dimension named-attribute embedding (interpretable, no neural model). Retrieval is hybrid: 0.40·cosine + 0.45·BM25 + 0.15·graph boost, with automatic deprecation filtering via valid_until. An eight-tool Python MCP server exposes the retrieval surface.
The earlier chunk-RAG approach exhibited five recurring failure modes: relevant documents ranked too low, duplicate chunks, excessive context, deprecated APIs in results, and application examples absent from retrieval. This project explores explicit graph structure and interpretable dimensions as remedies.
Eyal Nof. See CLAUDE.md for project-level Claude operating instructions and project.ctx for the architecture graph.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
Multiple MCP tools, persistent graph memory, token-saving data pointers, and more.
Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
