Skip to main content
Glama
Sign In

YouTube MCP by InsightfulPipe

by com.insightfulpipe
OverviewDiscussionsAdmin

Server Details

Hosted YouTube MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/youtube-mcp-server
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 4 tools

Disambiguation2/5

execute_action and query_data have virtually identical descriptions (both 'Step 3 (FINAL) of workflow', same two platforms, same required prerequisites), so an agent cannot tell which to call for a read vs. a write. Only prompts_menu and query_contexts have clearly distinct purposes, but query_contexts' 'actions_details' step also blurs into the execute step.

Naming Consistency3/5

Three tools use a verb_noun pattern (execute_action, query_contexts, query_data) but prompts_menu reverses to noun_noun, breaking the convention. The query_* pair differs only in the noun, which compounds the ambiguity rather than aiding recognition.

Tool Count3/5

Four tools is thin for a domain spanning analytics, channel/video/comment data, and a prompt catalog, and each tool crams many sub-operations into a 'request' parameter (prompts_menu alone bundles four operations). A dedicated split of the read vs. execute paths would earn its place better than the current packing.

Completeness3/5

The surface covers account discovery, schema introspection, data querying, and prompt listing, which is a workable read path. However, the apparent write/action path is indistinguishable from the query path, there is no dedicated tool for single-resource retrieval or workspace/brand management, and coverage of the 'youtube-data' write actions is never made explicit.

Available Tools

4 tools
execute_actionYouTube Execute ActionA
Destructive
Inspect

Execute YouTube action (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, channel_id AND available_requests

  2. request='actions_details' with platform + report_names or actions - Get detailed body structure

Two platforms: • youtube-analytics: channel_basic, video_performance, demographics, traffic_sources, revenue • youtube-data: channel_info, video_details, playlists, comments

Body must include 'platform' and 'action'. Follow the schema from step 2 exactly.

Inputs: body (required). Returns: object

prompts_menuYouTube PromptsA
Read-only
Inspect

Access YouTube prompt catalog with 4 operations:

  1. List Public Prompts: • request='menu' - No additional params needed • Returns: All public/system prompts available for YouTube

  2. List Custom Prompts: • request='menu', prompt_type='custom', workspace_id= • Returns: All custom prompts for the specified workspace

  3. Get Public Prompt Details: • request='prompt_details', prompt_id= • Returns: Full text/details of a public prompt

  4. Get Custom Prompt Details: • request='prompt_details', prompt_id=, is_custom=True, workspace_id= • Returns: Full text/details of a custom prompt

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsYouTube Setup HelperA
Read-only
Inspect

Helper for planning YouTube data queries.

Step 1: Get account information • request="accounts" - No extra params needed. Returns workspace_id, brand_id, channel_id, AND available_requests.

Step 2: Get detailed body structure for specific report(s)/action(s) • request="actions_details", platform="youtube-analytics" - List all available analytics reports • request="actions_details", platform="youtube-data" - List all available data actions • request="actions_details", platform="youtube-analytics", report_names=["channel_basic", "video_performance"] - Get schema for specific reports • request="actions_details", platform="youtube-data", actions=["channel_info", "video_details"] - Get schema for specific actions

Additional: Get brand guidelines • request="brands", brand_id=, workspace_id= - Get brand guidelines

Inputs: request (required), actions, brand_id, platform, +2 more. Returns: object

query_dataYouTube Data QueryA
Read-only
Inspect

Query YouTube data (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, channel_id AND available_requests

  2. request='actions_details' with platform + report_names or actions - Get detailed body structure

Two platforms: • youtube-analytics: channel_basic, video_performance, demographics, traffic_sources, revenue • youtube-data: channel_info, video_details, playlists, comments

Body must include 'platform' and 'action'. Follow the schema from step 2 exactly.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser
    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

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources