Skip to main content
Glama
Sign In
YouTube MCP

YouTube MCP

by pratikgh0se
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

youtube_creator_report

Read-only

Runs allowlisted YouTube Analytics reports for your owned channel, with metrics, dimensions, filters, sorting, and a default last-28-days range; invalid combinations are rejected before API calls.

Instructions

Run an allowlisted YouTube Analytics report for the owned channel (default: last 28 days). Metrics: views, estimatedMinutesWatched, averageViewDuration, averageViewPercentage, subscribersGained, subscribersLost, likes, comments, shares (viewerPercentage only with ageGroup/gender). Dimensions: day, month, video, country, deviceType, operatingSystem, insightTrafficSourceType, insightTrafficSourceDetail (needs one video plus an insightTrafficSourceType filter), ageGroup, gender, subscribedStatus, sharingService (shares only). Invalid combinations are rejected with invalid_input before any API call. Rows come back as objects keyed by column name.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "metrics": "<metrics>"
    },
    "name": "youtube_creator_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort keys, up to 4; prefix a key with - for descending, e.g. -views.
endDateNoEnd date, YYYY-MM-DD; defaults to today.
filtersNoOptional filters to narrow the report.
metricsYesYouTube Analytics metric names such as views, 1-12 items.
startDateNoStart date, YYYY-MM-DD; defaults to 28 days before endDate.
dimensionsNoYouTube Analytics dimension names to group by, up to 3.
maxResultsNoMaximum rows to return, 1-200; traffic-source-detail reports allow at most 25.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.3.1
    • addedInput schema / properties / dimensions / description
      Added value: +"YouTube Analytics dimension names to group by, up to 3."
    • addedInput schema / properties / endDate / description
      Added value: +"End date, YYYY-MM-DD; defaults to today."
    • addedInput schema / properties / filters / description
      Added value: +"Optional filters to narrow the report."
    • addedInput schema / properties / filters / properties / country / description
      Added value: +"Two-letter country code to filter by, e.g. US."
    • addedInput schema / properties / filters / properties / insightTrafficSourceType / description
      Added value: +"Traffic source type to filter by, e.g. YT_SEARCH."
    • addedInput schema / properties / filters / properties / videoIds / description
      Added value: +"Video IDs to limit the report to, 1-500 items."
    • addedInput schema / properties / maxResults / description
      Added value: +"Maximum rows to return, 1-200; traffic-source-detail reports allow at most 25."
    • addedInput schema / properties / metrics / description
      Added value: +"YouTube Analytics metric names such as views, 1-12 items."
    • addedInput schema / properties / sort / description
      Added value: +"Sort keys, up to 4; prefix a key with - for descending, e.g. -views."
    • addedInput schema / properties / startDate / description
      Added value: +"Start date, YYYY-MM-DD; defaults to 28 days before endDate."
  2. Addedv0.3.0

TDQS

A3.8/5.0
Behavior4/5

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

With readOnlyHint=true already declaring the safety profile, the description adds meaningful behavior: the report targets the owned channel, defaults to the last 28 days, rejects invalid combinations with invalid_input before any API call, and returns rows as objects keyed by column name. It does not discuss authentication scope or rate limits, but the read-only annotation lowers the burden.

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

Conciseness4/5

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

The description is front-loaded with the core action and default range, then lists metric/dimension constraints and validation behavior. It is dense and all content is relevant, though the single-paragraph list format is longer than ideal for quick scanning.

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?

For a complex, flexible Analytics query tool with seven parameters and no output schema, the description covers the key defaults, metric/dimension constraints, validation behavior, and return shape. It stops short of explicit sibling routing, which is the main remaining gap.

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 100%, so the baseline is 3, but the description adds valuable semantic constraints not fully captured by the schema: the allowed metrics and dimensions, viewerPercentage only with ageGroup/gender, insightTrafficSourceDetail requiring one video plus an insightTrafficSourceType filter, and sharingService being shares-only. It does not add much beyond the schema for sort, filters, or maxResults.

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 description states a specific verb and resource: run an allowlisted YouTube Analytics report for the owned channel. It lists the exact metrics and dimensions available, which makes the tool's scope concrete. It does not explicitly distinguish itself from sibling creator tools such as youtube_creator_overview, youtube_creator_top_videos, or youtube_creator_retention.

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 description implies this is the tool for custom Analytics reporting and gives useful constraints such as default date range and invalid combination rejection. However, it does not say when to use this versus youtube_creator_overview, youtube_creator_top_videos, or youtube_creator_retention, leaving alternative selection to inference.

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

Deploy Server

Other Tools