notebooklm-mcp

Overview Schema Source Related Servers Discussions Admin

Pipeline

pipeline

Run, list, or create multi-step NotebookLM workflows that chain tool actions and parameters to automate notebook tasks, including source ingestion and content generation.

Instructions

Manage and execute multi-step notebook pipelines.

Actions:

run: Execute a pipeline on a notebook
list: List all available pipelines (builtin and user-defined)
create: Save a user-defined pipeline (pipeline_name + steps; each step is {"action": , "params": {...}})

Input Schema

TableJSON Schema

Name	Required	Description
`steps`	No	Step definitions (required for action=create)
`action`	Yes	Operation to perform (run, list, create)
`input_url`	No	URL variable for pipelines that need it (replaces $INPUT_URL)
`description`	No	Pipeline description (for action=create)
`notebook_id`	No	Target notebook UUID (required for action=run)
`pipeline_name`	No	Pipeline name (required for action=run, e.g. "ingest-and-podcast")

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.15.1Oct 2, 2026

changedInput schema / properties / action / description

Previous value: -"Operation to perform (run, list)"New value: +"Operation to perform (run, list, create)"

addedInput schema / properties / description

Added value: +{
+  "default": "",
+  "description": "Pipeline description (for action=create)",
+  "type": "string"
+}

addedInput schema / properties / steps

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Step definitions (required for action=create)"
+}

Changed4 schema fields changedv0.11.2Sep 9, 2026

addedInput schema / properties / action / description
```
Added value: +"Operation to perform (run, list)"
```

addedInput schema / properties / input_url / description

Added value: +"URL variable for pipelines that need it (replaces $INPUT_URL)"

addedInput schema / properties / notebook_id / description

Added value: +"Target notebook UUID (required for action=run)"

addedInput schema / properties / pipeline_name / description

Added value: +"Pipeline name (required for action=run, e.g. \"ingest-and-podcast\")"

Addedv0.9.1Jul 22, 2026
Removedv0.8.9Jul 18, 2026

Changed4 schema fields changedv0.7.7Jun 20, 2026

removedInput schema / properties / action / description
```
Removed value: -"Operation to perform (run, list)"
```

removedInput schema / properties / input_url / description

Removed value: -"URL variable for pipelines that need it (replaces $INPUT_URL)"

removedInput schema / properties / notebook_id / description

Removed value: -"Target notebook UUID (required for action=run)"

removedInput schema / properties / pipeline_name / description

Removed value: -"Pipeline name (required for action=run, e.g. \"ingest-and-podcast\")"

First observedv0.6.13May 31, 2026

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully discloses that pipelines are composed of other tool calls ("each step is {action: <tool name>, params: {...}}") and that list covers both builtin and user-defined pipelines. It omits execution semantics such as whether run is synchronous/long-running, failure behavior, or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One framing sentence followed by a tight bulleted action list. Purpose is front-loaded and every line carries information; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All six parameters are documented in the schema and an output schema exists, so return values need not be explained. The description covers all three actions and the step format, leaving only execution-model details (sync vs async, error handling) unaddressed, which is a minor gap for a multi-action tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is already 100%, so the baseline is 3. The description earns above baseline by explaining the internal shape of `steps` (an array of {action, params} objects) and by tying pipeline_name and steps to action=create, which the schema alone does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening line states a specific verb+resource ("Manage and execute multi-step notebook pipelines") and the action bullets clarify what run/list/create each do. It does not differentiate itself from potentially overlapping siblings like `batch`, but no sibling directly competes for pipeline management, so the purpose is clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The action list implies when each mode applies (run executes, list enumerates, create persists), which is reasonable implied guidance. However, there is no explicit guidance on when to use this tool versus chaining individual tool calls manually or using `batch`, and no exclusions or prerequisites are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.