Skip to main content
Glama
claude-world

notebooklm-skill

by claude-world
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
nlm_create_notebookA

Create a notebook with optional URL, raw-text, and local-file sources.

Returns per-source outcomes and truthful requested/succeeded/failed counts.

nlm_listA

List NotebookLM notebooks with IDs, titles, and source counts.

nlm_deleteC

Permanently delete a notebook only when confirm is true.

nlm_add_sourceC

Add exactly one URL, text, or local file source to a notebook.

nlm_askC

Ask a source-grounded question and return answer citations.

nlm_summarizeD

Return the NotebookLM-generated summary for a notebook.

nlm_list_sourcesC

List ingested sources with current kind and processing status.

nlm_generateA

Generate an artifact, optionally waiting for completion.

type supports audio, video, cinematic, slides, report, study-guide, quiz, flashcards, mind-map, infographic, and data-table. options may contain type-specific keys such as audio_format, audio_length, video_format, video_style, slide_format, slide_length, report_format, custom_prompt, quantity, difficulty, orientation, detail_level, or style. Set wait=false to return the task ID immediately for long media jobs.

nlm_downloadB

Download an exact artifact ID (or latest) to a local path.

Existing files and symlinks are rejected unless the safe overwrite rules permit the path. Formats: slides=pdf/pptx; quiz/flashcards=json/markdown/html.

nlm_list_artifactsC

List actual generated artifacts, optionally filtered by canonical type.

nlm_researchC

Run pinned web research, wait for a terminal state, and import findings.

nlm_research_pipelineC

Create a notebook, ingest URLs, ask questions, and assemble content.

nlm_trend_researchC

Fetch trend-pulse topics, research/import each, and create grounded drafts.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 13 tools

Disambiguation5/5

All tools have clearly distinct purposes: creating, listing, deleting notebooks; adding/list sources; asking questions; summarizing; generating artifacts; downloading; and various research pipelines. No significant overlap.

Naming Consistency4/5

All tools use 'nlm_' prefix with snake_case verbs (e.g., nlm_list, nlm_ask) or verb_noun phrases (e.g., nlm_create_notebook). Minor inconsistency: some are just verbs while others include nouns, but pattern is predictable.

Tool Count5/5

13 tools is appropriate for a notebook management and research service. Each tool covers a distinct operation without redundancy.

Completeness4/5

Covers core CRUD for notebooks, source management, Q&A, summary, artifact generation, and download. Missing minor operations like source deletion or notebook renaming.

Maintenance

ActivityStale
ResponsivenessSlow

Resources