Production API v1

Expert clip retrieval API

Authenticate with Authorization: Bearer <api_key> or x-api-key. Base URL: https://www.youtubetimesearch.com/api/v1

← API preview overview

Pricing tiers (monthly)

TierRequests / month
free100
pro5,000
team50,000
enterprise500,000

Enterprise limits are configurable per key. Responses include x-quota-limit, x-quota-used, x-quota-remaining. HTTP 429 when exceeded.

Local API keys

npm run api:create-key -- --label "My app" --tier free
npm run api:list-keys
npm run api:revoke-key -- --id key_xxx

GET /api/v1/transcript

Fetch cached or live YouTube transcript segments for a video.

videoId (required) or url; maxSegments optional

curl

curl -s -H "Authorization: Bearer YOUR_API_KEY" \
  "https://www.youtubetimesearch.com/api/v1/transcript?videoId=dQw4w9WgXcQ"

JavaScript

const res = await fetch(
  `https://www.youtubetimesearch.com/api/v1/transcript?videoId=dQw4w9WgXcQ`,
  { headers: { Authorization: `Bearer ${apiKey}` } }
);
const data = await res.json();

Python

import requests
r = requests.get(
    "https://www.youtubetimesearch.com/api/v1/transcript",
    params={"videoId": "dQw4w9WgXcQ"},
    headers={"Authorization": f"Bearer {api_key}"},
)
print(r.json())

GET /api/v1/search

Semantic + keyword search across indexed expert transcript moments.

q (required), limit (default 10, max 50)

curl

curl -s -H "x-api-key: YOUR_API_KEY" \
  "https://www.youtubetimesearch.com/api/v1/search?q=rag+vs+mcp&limit=5"

JavaScript

const res = await fetch(
  `https://www.youtubetimesearch.com/api/v1/search?q=${encodeURIComponent("rag vs mcp")}&limit=5`,
  { headers: { "x-api-key": apiKey } }
);

Python

requests.get("https://www.youtubetimesearch.com/api/v1/search", params={"q": "rag vs mcp", "limit": 5}, headers={"x-api-key": api_key})

POST /api/v1/answer

Authority-ranked answer with timestamped source moment and supporting clips.

JSON body: { q, limit? } — GET also supported with ?q=

curl

curl -s -X POST -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"q":"rag vs mcp","limit":8}' \
  "https://www.youtubetimesearch.com/api/v1/answer"

JavaScript

await fetch(`https://www.youtubetimesearch.com/api/v1/answer`, {
  method: "POST",
  headers: { Authorization: `Bearer ${apiKey}`, "Content-Type": "application/json" },
  body: JSON.stringify({ q: "rag vs mcp", limit: 8 }),
});

Python

requests.post("https://www.youtubetimesearch.com/api/v1/answer", json={"q": "rag vs mcp"}, headers={"Authorization": f"Bearer {api_key}"})
Every search/answer hit includes an authority object: authorityScore, sourceType, sourceName, whyThisSource, topicCluster, demandIntent, freshnessScore, citationUrl, timestampUrl, transcriptExcerpt, confidenceLabel. Answers add citedMoments, rejectedSourcesSummary, uncertaintyNotes, followUpQueries, and sourceDiversityScore.

Trust product layer for rag vs mcp — cluster mcp-agents

Why this answer is trustworthy

Trust 71%Enterprise readiness 90%Evidence strength 64%Diversity 100%

Why this answer won

Tier-1 expert moment (Anthropic) paired with hard doc citations; fusion=rrf and top_k=20 in operational excerpt.

Configs used

  • top_k=8

    corpus · confidence 43%

Benchmark evidence

  • faithfulness=0.82

    observed in cited evidence

    Sam Witteveen

Failure fixes

No incident remediation path in cited evidence.

Expert video corroboration

Building with MCP and Claude API — tool invocation

Sam Witteveen

https://www.youtube.com/watch?v=aZLr962R6Ag&t=638

Contradictory evidence

No contradictory expert framing detected.

Trace lineage

  1. queryretrieval.request

    hybrid_search

    rag vs mcp

  2. retrieve_hit_1retrieval.candidate

    Sam Witteveen

    12:34 · score 0.82

  3. synthesisanswer.operational_gate

    mcp_tool_orchestration

    passed

Citation quality (primary)

RAG vs MCP — expert walkthrough

Authority 82%· high

MCP is a protocol for tool context, while RAG retrieves documents at answer time. trace id visible in LangSmith retrieve span; faithfulness=0.82.

Source type:
youtube_expert
Cluster:
mcp-agents

Authority 82% · high confidence

Winning evidence

  • expert Building with MCP and Claude API — tool invocation90%
  • citation RAG vs MCP — expert walkthrough82%
  • config top_k=843%
  • trace LangSmith32%
  • trace retrieve span32%

Rejected evidence

  • Excluded candidates: lower rank or diversity cap

Operational checklist

  • Hard citations paired1 cited moment(s)
  • Configuration evidence
  • Benchmark / metric evidence
  • Trace / observability lineage
  • Failure / remediation evidence
  • Expert video corroborationBuilding with MCP and Claude API — tool invocation
  • Source diversity100%
  • Contradictions reviewed

Uncertainty

  • Static trust demo; run live /api/v1/answer for production trust envelope.

Need higher limits or enterprise SLA?

Contact us for team keys, custom quotas, and billing integration.