YouTube

Live

OAUTH 2.0

VIDEO

Media

Every video, channel, and analytics report your content team manages lives in YouTube. YouTube MCP gives your agent authenticated access to video data scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the YouTube account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: Permissions enforced. 90-day audit trail.
YouTube
agent · Acme Q3
Run
Which videos had the highest CTR this month and what was the average watch time?
S
youtube_analytics_get
820ms
Content agent
Top 3 CTR this month: 'How We Ship 10x Faster' (8.4% CTR, 6.2 min avg watch time), 'Auth in 5 Minutes' (7.1% CTR, 4.8 min), 'AI Agent Demo' (6.8% CTR, 7.1 min). Channel average CTR: 5.2%.
Sources: YouTube Analytics, this month
youtubemcp
3 videos
18:29
Message Claude...

Tools your content agent reaches for on YouTube, scoped per user.

CALL ANY TOOL
List and inspect videos, pull channel and video analytics, search YouTube, and read comments.
youtube_videos_list
List videos
List YouTube videos for a channel with filter options.
Parameters
Name
Type
Required
Description
channel_id
string
Optional
YouTube channel ID (default: authorized user's channel)
max_results
integer
Optional
Max videos to return
order
string
Optional
Order by: date, rating, viewCount, relevance
youtube_video_get
Get video
youtube_analytics_get
Get video analytics
youtube_search
Search YouTube
youtube_comments_list
List comments
Build your Agent
Drop the toolkit in, point it at the user, and your content agent can use YouTube from the first run.
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["youtube"], toolNames: ["youtube_videos_list", "youtube_video_get", "youtube_analytics_get"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["youtube"], toolNames: ["youtube_videos_list", "youtube_video_get", "youtube_analytics_get"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["youtube"], toolNames: ["youtube_videos_list", "youtube_video_get", "youtube_analytics_get"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/youtube",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using YouTube.
Videos & analytics
Copy the prompt
Copied
List all videos on my channel.
Copy the prompt
Copied
Which videos had the most views this month?
Copy the prompt
Copied
Get CTR and watch time for [video id].
Copy the prompt
Copied
Channel analytics for the last 30 days.
Search & discovery
Copy the prompt
Copied
Search YouTube for [query].
Copy the prompt
Copied
Find videos with [keyword] in title.
Copy the prompt
Copied
Get metadata for video [id].
Copy the prompt
Copied
List all playlists on [channel].
Engagement & comments
Copy the prompt
Copied
List top comments on [video id].
Copy the prompt
Copied
Which videos have the most comments this month?
Copy the prompt
Copied
Subscribers gained this week.
Copy the prompt
Copied
Videos with finish rate above 60%.
SEE HOW AUTH WORKS
Users authorize YouTube once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
YouTube
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
YouTube
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
YouTube
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
YouTube
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other content agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
GTM
HubSpot to Slack updates agent
Watch HubSpot deal stage changes and post structured updates to the right Slack channel. Reps stop checking the CRM all day.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
YouTube today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access YouTube as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the YouTube oauth 2.0 stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in YouTube?
Yes. Pass a tool name filter to listScopedTools so the content agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches YouTube.
What happens when a user revokes YouTube access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent access analytics for channels the user does not own?
No. YouTube Analytics API only returns data for channels the authorizing user manages. Public video metadata is accessible for any video, but analytics require ownership or edit access to the channel.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""youtube"": {
""url"": ""https://mcp.scalekit.com/youtube"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.youtube]
url = ""https://mcp.scalekit.com/youtube""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""youtube"": {
""url"": ""https://mcp.scalekit.com/youtube"",
""type"": ""http""
}
}
}