$ loading_
Ingest documents into notebooks and run semantic retrieval on ranked raw chunks.
This tool is described as a self-hosted, notebook-scoped RAG MCP server with no declared API keys or remote endpoints, and no clear signs of high-risk data exfiltration. The main concerns are the inherent local code execution and document ingestion/search capabilities of an MCP tool, plus weaker trust signals from a third-party registry listing with minimal community/maintenance evidence, so the overall posture is caution rather than high risk.
The material explicitly states that no keys or environment variables are required, and there is no indication of API tokens, account credentials, or third-party authorization being needed, so credential exposure appears limited.
It is described as self-hosted and no remote host is declared; based on the available material, there is no factual indication that user data is sent to external services.
The system checks indicate it executes code; as an MCP server, it typically needs to start local processes and run service logic. This is an inherent capability of such tools, and the material does not show any abnormal system permissions beyond its stated function.
Its functionality includes ingesting documents into named notebooks and performing semantic search, which implies access to user-provided local documents and possible storage of indexes/chunks. Based on the description, this scope aligns with a RAG tool, but the actual read/write paths and persistence locations should still be verified.
There is a public GitHub repository available for review, which is a positive sign; however, the source is only a third-party registry listing, the README is absent, the license is unspecified, community adoption is 0 stars, and maintenance status is unknown, so trust and maintainability signals are weak and the code/dependencies should be reviewed directly.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ScribblesLM" yet — see the docs or source repo.
Please ingest the following product specs, meeting notes, and technical docs into a notebook named "project-alpha" and return the ingestion result and indexing status for each file.
Returns document ingestion status, the target notebook name, and index confirmation for later retrieval.
Search the "project-alpha" notebook for "root cause of user permission sync failure" and return the most relevant raw text chunks ranked by relevance.
Returns a relevance-ranked list of raw chunks for manual review or downstream QA use.
Ingest paper abstracts, experiment logs, and reports into the "llm-eval" notebook, then search for "evaluation methods for contextual retrieval" and output the matching raw chunks.
First stores the materials, then returns the most relevant raw content chunks with ranking results.
Automate NotebookLM to manage sources, answer questions, and generate audio overviews.
Connect to Google NotebookLM to organize sources and generate learning outputs.
Connect to Google NotebookLM for source ingestion, querying, and audio summary generation.
Search, read, and list Obsidian notes with natural language semantic retrieval.
Manage NotebookLM notebooks, sources, chats, and research with natural language.
Control Google NotebookLM with AI for notebooks, sources, and audio generation.