YouTube Studio MCP

Overview Schema Source Related Servers Discussions Admin

Sign in to YouTube

authenticate

Launch Google sign-in in your browser and return the URL for granting access to your own YouTube channel analytics, then verify sign-in status before reading data.

Instructions

Start Google sign-in in the user's browser and return the sign-in URL immediately.

The user must approve access in the browser (choosing the account or Brand Account that owns the channel). Afterwards call get_auth_status to confirm. Only works when the MCP server runs on the user's own computer. Signing in again replaces the stored token.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "authenticate"
  }
}

Input Schema

Name	Required	Description	Default
`include_revenue`	No	Also request read access to revenue reports (only useful for monetized channels).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare the generic profile (openWorldHint, not read-only, not idempotent). The description adds the non-obvious behavior the agent cannot infer: the call returns before authentication finishes, the flow requires out-of-band browser approval, local execution is mandatory, and re-authenticating overwrites the stored token.

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?

Four short sentences ordered by what the agent needs first: what happens, what the user must do, what to call next, then constraints and side effects. No filler and no restatement of the tool name.

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

Completeness5/5

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

An output schema exists, so return values need no explanation, and the description covers the remaining risks: environment limits, the human-approval dependency, and token replacement on repeat calls. Nothing an agent needs to invoke this correctly is missing.

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

Parameters3/5

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

The single parameter is fully documented in the schema, including its default of true and the note that it only matters for monetized channels. The description adds nothing about include_revenue, so the schema carries this dimension alone — the baseline for 100% coverage.

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

Purpose5/5

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

States a specific verb and resource ('Start Google sign-in') plus the immediate observable effect ('return the sign-in URL'), which no sibling name suggests. It also separates itself from get_auth_status, which is named as the confirmation step rather than the initiation step.

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

Usage Guidelines5/5

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

Gives explicit sequencing ('Afterwards call `get_auth_status` to confirm') and a hard precondition ('Only works when the MCP server runs on the user's own computer'). It also tells the agent what the human must do mid-flow (approve access, pick the account or Brand Account owning the channel), which is the main failure mode.

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