{
  "markdown": "<!-- mcp-name: com.transcriptapi/youtube-transcript-and-youtube-search -->\n\n<p align=\"center\">\n  <a href=\"https://transcriptapi.com\">\n    <img src=\"public/brand/logo-512.png\" width=\"160\" height=\"160\" alt=\"TranscriptAPI\" />\n  </a>\n</p>\n\n<h1 align=\"center\">YouTube Transcript + YouTube Search MCP for AI Agents</h1>\n\n<p align=\"center\">\n  <b>The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free.</b><br/>\n  Six tools — transcripts, video search, channel browsing, in-channel search, playlist extraction, and new-upload polling — for Claude, ChatGPT, Cursor, VS Code, Claude Code, and 20+ clients.\n</p>\n\n<p align=\"center\">\n  <a href=\"https://cursor.com/en/install-mcp?name=transcript-api&config=eyJ1cmwiOiJodHRwczovL3RyYW5zY3JpcHRhcGkuY29tL21jcCJ9\"><img alt=\"Install in Cursor\" src=\"https://img.shields.io/badge/Cursor-Install_MCP-000000?style=for-the-badge&logo=cursor&logoColor=white\"/></a>\n  <a href=\"https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%7B%22name%22%3A%22transcript-api%22%2C%22url%22%3A%22https%3A%2F%2Ftranscriptapi.com%2Fmcp%22%7D\"><img alt=\"Install in VS Code\" src=\"https://img.shields.io/badge/VS_Code-Install_MCP-0098FF?style=for-the-badge&logo=visualstudiocode&logoColor=white\"/></a>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://transcriptapi.com\"><img src=\"https://img.shields.io/badge/Website-transcriptapi.com-FF3B00?style=for-the-badge\" alt=\"Website\"/></a>\n  <a href=\"https://transcriptapi.com/docs\"><img src=\"https://img.shields.io/badge/Docs-API_Reference-06B6D4?style=for-the-badge&logo=readthedocs&logoColor=white\" alt=\"Docs\"/></a>\n  <a href=\"https://transcriptapi.com/swagger\"><img src=\"https://img.shields.io/badge/Swagger-Try_API-85EA2D?style=for-the-badge&logo=swagger&logoColor=white\" alt=\"Swagger\"/></a>\n  <a href=\"./LICENSE\"><img src=\"https://img.shields.io/badge/License-MIT-4CAF50?style=for-the-badge\" alt=\"MIT License\"/></a>\n</p>\n\n> **Powering 15M+ transcripts every month** · 500K+ transcripts processed daily · 49ms median response time\n> Trusted in production by [youtubetotranscript.com](https://youtubetotranscript.com) (~11M/mo) and [recapio.com](https://recapio.com) (~2.8M/mo).\n\n---\n\n## Why TranscriptAPI MCP\n\nMost YouTube MCP servers do one thing — pull a single transcript. **TranscriptAPI MCP is a full toolkit**: transcripts, video search, channel search, channel browsing, playlist extraction, and free RSS-based upload tracking — all from one remote endpoint, all designed for AI agents.\n\n|                                          | TranscriptAPI MCP | Typical YouTube MCP |\n| ---------------------------------------- | ----------------- | ------------------- |\n| Hosting                                  | ✅ Remote (no local install) | ❌ Local stdio install |\n| Tools                                    | ✅ 6 tools         | ❌ 1 (transcript only) |\n| YouTube search                           | ✅ Yes             | ❌ No |\n| Channel & playlist extraction            | ✅ Yes             | ❌ No |\n| Latest-uploads monitoring (free)         | ✅ Yes             | ❌ No |\n| OAuth 2.1 + API key auth                 | ✅ Both            | ❌ Usually neither |\n| Production scale (15M+ req/mo)           | ✅ Yes             | ❌ Hobbyist scrapers |\n| Works on mobile Claude & web Claude      | ✅ Yes             | ❌ No |\n| Agent-friendly error messages            | ✅ Yes             | ❌ Bare HTTP codes |\n\n**Quick taste:**\n\n```txt\nFind Andrew Huberman's three most-viewed videos about sleep,\nget the transcript of each, and write a 5-bullet comparison.\n```\n\nThat single prompt uses 3 of our 6 tools — `search_youtube`, `search_channel_videos`, `get_youtube_transcript` — without you writing a line of code.\n\n---\n\n## 🧩 Install as an Agent Plugin <sub>· **easiest**</sub>\n\nThis repository root is a conformant **[Agent Plugins 1.0.0](https://agent-plugins.org/specification)** package — the portable format published 2026-08-06 and supported by ChatGPT, Codex, Cursor, GitHub Copilot, Kiro and VS Code. One install gets you the MCP server **and** a bundled `youtube` skill that teaches your agent when to use each tool and how not to waste credits.\n\n```text\nplugin.json                    # Agent Plugins 1.0.0 manifest\nmcp.json                       # hosted MCP server, streamable-http, OAuth (no keys)\nskills/youtube/SKILL.md        # when + how to use the 6 tools\n.cursor-plugin/plugin.json     # Cursor plugin manifest, same MCP + skill (+ marketplace.json)\n```\n\n**VS Code** — Command Palette → **Chat: Install Plugin From Source**, then paste:\n\n```txt\nhttps://github.com/ZeroPointRepo/youtube-mcp\n```\n\nOr register a local clone in `settings.json`:\n\n```json\n\"chat.pluginLocations\": { \"/absolute/path/to/youtube-mcp\": true }\n```\n\n**Cursor** — **Customize** in the sidebar → find the plugin → **Install**. For a local clone:\n\n```bash\ngit clone https://github.com/ZeroPointRepo/youtube-mcp ~/.cursor/plugins/local/transcriptapi\n```\n\nThen **Developer: Reload Window**.\n\n**Add to Cursor** — MCP server only, no clone. Paste this deeplink into your browser:\n\n```txt\ncursor://anysphere.cursor-deeplink/mcp/install?name=transcriptapi&config=eyJ1cmwiOiJodHRwczovL3RyYW5zY3JpcHRhcGkuY29tL21jcCJ9\n```\n\n**ChatGPT, Codex, GitHub Copilot, Kiro, any other client** — point your client's plugin mechanism at this repository, or at a local clone. Agent Plugins 1.0.0 standardizes the *package format*, not installation, so each client owns its own install flow.\n\n### 30-second example\n\n```txt\nSummarize this video for me: https://youtu.be/dQw4w9WgXcQ\n```\n\nThe agent calls `get_youtube_transcript`, gets the full timestamped transcript and summarizes it. **No API key to configure** — the first call opens an OAuth sign-in (free account, 100 credits, no card). Then try:\n\n```txt\nWhat has @TED posted in the last month?     → get_channel_latest_videos (free)\nFind talks on protein folding, summarize the best three.\n                                             → search_youtube, then transcripts\n```\n\nThere are **no credentials in this package** — Agent Plugins 1.0.0 forbids embedded secrets, and authorization is client-managed. Verify the package yourself:\n\n```bash\ncurl -sO https://agent-plugins.org/schemas/1.0.0/plugin.schema.json\ncurl -sO https://agent-plugins.org/schemas/1.0.0/mcp.schema.json\nnpx ajv-cli@5 validate --spec=draft2020 -s plugin.schema.json -d plugin.json\nnpx ajv-cli@5 validate --spec=draft2020 -s mcp.schema.json    -d mcp.json\n```\n\n---\n\n## 🛠️ Quick Install\n\n> **Requirements:**\n>\n> - A TranscriptAPI account ([sign up free](https://transcriptapi.com) — first 100 credits free)\n> - An API key from your [dashboard](https://transcriptapi.com/dashboard/api-keys) **OR** use OAuth (Claude, ChatGPT)\n\n> **Recommended: Add a Rule to Auto-Invoke TranscriptAPI**\n>\n> Add this rule to your AI client so you don't need to explicitly ask for transcripts:\n>\n> ```txt\n> When I share a YouTube URL, automatically use the TranscriptAPI MCP tool\n> to fetch the transcript before responding. This applies to any video analysis,\n> summarization, or question about YouTube content.\n> ```\n\n<details>\n<summary><b>Install in Cursor (One-Click / Manual)</b></summary>\n\n**One-Click Install:**\n\n[![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=transcript-api&config=eyJ1cmwiOiJodHRwczovL3RyYW5zY3JpcHRhcGkuY29tL21jcCJ9)\n\n**Manual Configuration:**\n\nGo to: `Settings` → `Features` → `MCP` → `Add New MCP Server`\n\n- **Name:** `transcript-api`\n- **Type:** `SSE` (Remote)\n- **URL:** `https://transcriptapi.com/mcp`\n\nOr edit `~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Claude (Desktop & Web) — Recommended</b></summary>\n\nClaude supports adding MCP servers directly via the \"Custom Connector\" UI.\n\n**Quick Setup:**\n\n1. Open Claude Settings (click your profile icon → Settings)\n2. Go to **Connectors** → **Add custom connector**\n3. Enter the following details:\n   - **Name:** `TranscriptAPI`\n   - **URL:** `https://transcriptapi.com/mcp`\n4. Click **Add**, then click **Connect** to authorize via your browser.\n5. (Optional) In the connector settings, change permissions to \"Allow unsupervised\" for seamless usage.\n\n**Full Guide:** [Claude Integration Guide →](https://transcriptapi.com/docs/mcp/claude)\n\n</details>\n\n<details>\n<summary><b>Install in Claude Code (CLI)</b></summary>\n\n```sh\nclaude mcp add --transport http transcript-api https://transcriptapi.com/mcp\n```\n\n</details>\n\n<details>\n<summary><b>Install in ChatGPT</b></summary>\n\nChatGPT supports OAuth for secure authentication. Enable **Developer Mode** in ChatGPT settings first.\n\n**Quick Setup:**\n\n1. In ChatGPT, go to `Settings` → `Connected Apps` → `Add`\n2. Enter the MCP Server URL: `https://transcriptapi.com/mcp`\n3. **Client ID & Secret are optional:**\n   - **Leave them blank** to use Dynamic Client Registration (recommended/simpler).\n   - **(Advanced)** Or enter Client ID & Secret from your [dashboard](https://transcriptapi.com/dashboard/mcp-integration) for static registration.\n4. Click **Add** and authorize via the browser popup.\n\n**Full Guide:** [ChatGPT Integration Guide →](https://transcriptapi.com/docs/mcp/chatgpt)\n\n</details>\n\n<details>\n<summary><b>Install in VS Code</b></summary>\n\n[<img alt=\"Install in VS Code\" src=\"https://img.shields.io/badge/VS_Code-Install_TranscriptAPI_MCP-0098FF?style=for-the-badge&logo=visualstudiocode&logoColor=white\">](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%7B%22name%22%3A%22transcript-api%22%2C%22url%22%3A%22https%3A%2F%2Ftranscriptapi.com%2Fmcp%22%7D)\n\nOr add this to VS Code user settings (`settings.json`):\n\n```json\n\"mcp.servers\": {\n  \"transcript-api\": {\n    \"type\": \"http\",\n    \"url\": \"https://transcriptapi.com/mcp\",\n    \"headers\": {\n      \"Authorization\": \"Bearer YOUR_API_KEY\"\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in OpenAI Agent Builder</b></summary>\n\nOpenAI Agent Builder currently requires API Key authentication (OAuth not yet supported).\n\n1. Create a new Agent\n2. Under \"Actions\" or \"Tools\", add a new **MCP Server**\n3. URL: `https://transcriptapi.com/mcp`\n4. Auth Type: **API Key**\n5. Paste your API Key from the [dashboard](https://transcriptapi.com/dashboard/api-keys)\n\n[Step-by-Step Guide →](https://transcriptapi.com/docs/mcp/openai-agent-builder)\n\n</details>\n\n<details>\n<summary><b>Install in Windsurf</b></summary>\n\nAdd to `~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"serverUrl\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Cline</b></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"type\": \"streamableHttp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Zed</b></summary>\n\nIn Zed `settings.json`:\n\n```json\n{\n  \"context_servers\": {\n    \"transcript-api\": {\n      \"source\": \"remote\",\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Roo Code</b></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Amp</b></summary>\n\n```sh\namp mcp add transcript-api https://transcriptapi.com/mcp --header \"Authorization: Bearer YOUR_API_KEY\"\n```\n\n</details>\n\n<details>\n<summary><b>Install in Augment Code</b></summary>\n\nIn `settings.json` under `augment.advanced`:\n\n```json\n\"augment.advanced\": {\n  \"mcpServers\": [\n    {\n      \"name\": \"transcript-api\",\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  ]\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Kilo Code</b></summary>\n\nIn `.kilocode/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in JetBrains AI Assistant</b></summary>\n\nIn Settings → Tools → AI Assistant → MCP:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Gemini CLI</b></summary>\n\nIn `~/.gemini/settings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"httpUrl\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Qwen Coder</b></summary>\n\nIn `~/.qwen/settings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"httpUrl\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Google Antigravity</b></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"serverUrl\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Trae</b></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in LM Studio</b></summary>\n\nIn `mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in BoltAI</b></summary>\n\nIn Plugins → JSON Config:\n\n```json\n{\n  \"mcpServers\": {\n    \"transcript-api\": {\n      \"url\": \"https://transcriptapi.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Warp</b></summary>\n\nIn Settings → AI → MCP:\n\n```json\n{\n  \"transcript-api\": {\n    \"url\": \"https://transcriptapi.com/mcp\",\n    \"headers\": {\n      \"Authorization\": \"Bearer YOUR_API_KEY\"\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Install in Perplexity Desktop</b></summary>\n\nIn Settings → Connectors → Advanced:\n\n```json\n{\n  \"url\": \"https://transcriptapi.com/mcp\",\n  \"headers\": {\n    \"Authorization\": \"Bearer YOUR_API_KEY\"\n  }\n}\n```\n\n</details>\n\n---\n\n## 🔐 Authentication\n\n### API Key\n\nSimple and universal. Works with every MCP client.\n\n1. Get your API key from your [dashboard](https://transcriptapi.com/dashboard/api-keys)\n2. Keys start with `sk_` prefix\n3. Add to config as a Bearer token:\n\n```json\n\"headers\": {\n  \"Authorization\": \"Bearer sk_your_api_key_here\"\n}\n```\n\n> **Security:** Store keys in environment variables where possible and never commit them to version control.\n\n### OAuth 2.1\n\nAutomatic, secure authentication without manual key management.\n\n**Dynamic Client Registration (DCR):**\n\n- Supported by: Claude Desktop, Claude Web, ChatGPT\n- Just add the MCP URL — client auto-registers\n- No credentials needed\n- You'll authorize once via browser redirect\n\n**Static Client Registration:**\n\n- Supported by: ChatGPT (optional)\n- Get Client ID + Secret from the [MCP Integration Dashboard](https://transcriptapi.com/dashboard/mcp-integration)\n- More control over client identity\n\nFull reference: [Authentication docs →](https://transcriptapi.com/docs/mcp/claude)\n\n---\n\n## 🧰 Available Tools\n\nAll six tools are exposed automatically once you connect. **1 credit = 1 successful (HTTP 200) request.** Failed/rate-limited calls do not consume credits.\n\n### 1. `get_youtube_transcript`\n\nFetch the transcript for any YouTube video — as markdown (with metadata) or structured JSON. Drop the output straight into summarizers, search indexes, or AI pipelines.\n\n| Parameter           | Type    | Default      | Description                                    |\n| ------------------- | ------- | ------------ | ---------------------------------------------- |\n| `video_url`         | string  | **required** | YouTube URL (full or short) or 11-char video ID |\n| `send_metadata`     | boolean | `true`       | Include video title, author, thumbnail         |\n| `format`            | string  | `\"text\"`     | `\"text\"` (markdown) or `\"json\"`                |\n| `include_timestamp` | boolean | `true`       | Add timestamps to each segment                 |\n\n**Cost:** 1 credit per successful request.\n\n**Example output (markdown):**\n\n```markdown\n# Metadata\n\n## Title: Rick Astley - Never Gonna Give You Up\n## Author: RickAstleyVEVO\n\n# Transcript\n\n[0.0s] Never gonna give you up\n[4.12s] Never gonna let you down\n```\n\n**Example output (JSON):**\n\n```json\n{\n  \"transcript\": [\n    { \"text\": \"Never gonna give you up\", \"start\": 0.0, \"duration\": 4.12 },\n    { \"text\": \"Never gonna let you down\", \"start\": 4.12, \"duration\": 3.85 }\n  ],\n  \"metadata\": { \"title\": \"Rick Astley...\", \"author_name\": \"RickAstleyVEVO\" }\n}\n```\n\n---\n\n### 2. `search_youtube`\n\nSearch YouTube for videos or channels. Filter by type and paginate with a continuation token — perfect for discovery, research, and building content pipelines.\n\n| Parameter      | Type   | Default      | Description                          |\n| -------------- | ------ | ------------ | ------------------------------------ |\n| `query`        | string | **required** | Search query                         |\n| `search_type`  | string | `\"video\"`    | `\"video\"` or `\"channel\"`             |\n| `continuation` | string | `null`       | Token from a prior call for next page |\n\n**Cost:** 1 credit per page (~20 results per page).\n\n**Example prompt:**\n\n```txt\nSearch YouTube for \"transformer architecture explained\" and pick the\ntop 3 results by relevance.\n```\n\n---\n\n### 3. `get_channel_latest_videos` <sub>· **FREE**</sub>\n\nGet the ~15 most recent uploads from any channel via RSS — no credits required. Perfect for monitoring, daily recaps, or triggering downstream pipelines.\n\n| Parameter | Type   | Default      | Description                                  |\n| --------- | ------ | ------------ | -------------------------------------------- |\n| `channel` | string | **required** | `@handle`, channel URL, or `UC…` channel ID |\n\n**Cost:** Free.\n\n**Example prompt:**\n\n```txt\nEvery morning, list new uploads from @lexfridman and @hubermanlab.\n```\n\n---\n\n### 4. `search_channel_videos`\n\nSearch inside one specific channel for videos matching a query. Great for researching a creator's content or finding niche topics in large channels.\n\n| Parameter      | Type   | Default      | Description                          |\n| -------------- | ------ | ------------ | ------------------------------------ |\n| `channel`      | string | **required** | `@handle`, channel URL, or `UC…` ID |\n| `query`        | string | **required** | Query to search within the channel   |\n| `continuation` | string | `null`       | Pagination token                     |\n\n**Cost:** 1 credit per page (~30 results per page).\n\n**Example prompt:**\n\n```txt\nOn Andrew Huberman's channel, find every video about sleep.\n```\n\n---\n\n### 5. `list_channel_videos`\n\nList every video on a channel, ~100 per page. Ideal for building databases, bulk transcript extraction, or auditing a channel's full content library.\n\n| Parameter      | Type   | Default      | Description                          |\n| -------------- | ------ | ------------ | ------------------------------------ |\n| `channel`      | string | **required** | `@handle`, channel URL, or `UC…` ID |\n| `continuation` | string | `null`       | Pagination token                     |\n\n**Cost:** 1 credit per page (~100 results per page).\n\n---\n\n### 6. `list_playlist_videos`\n\nGet every video in a YouTube playlist (PL/UU/LL/FL/OL IDs supported). Process entire courses, lecture series, or curated collections in a single call.\n\n| Parameter      | Type   | Default      | Description                  |\n| -------------- | ------ | ------------ | ---------------------------- |\n| `playlist`     | string | **required** | Playlist URL or playlist ID  |\n| `continuation` | string | `null`       | Pagination token             |\n\n**Cost:** 1 credit per page (~100 results per page).\n\n---\n\n## 💡 Use Cases & Prompts\n\n| Use Case                       | Example Prompt                                                                                  |\n| ------------------------------ | ----------------------------------------------------------------------------------------------- |\n| 📝 **Summarize a video**       | \"Summarize the key points from this video: [URL]\"                                               |\n| 🔍 **Research a topic**        | \"Search YouTube for the 5 most-watched videos on neural radiance fields; summarize each.\"        |\n| 🧠 **Study notes**             | \"Create study notes from this MIT lecture series playlist: [PLAYLIST URL]\"                       |\n| ⚖️ **Compare perspectives**    | \"Compare arguments in these two videos: [URL1] [URL2]\"                                          |\n| 🌐 **Translate**               | \"Translate this video's transcript to Spanish: [URL]\"                                           |\n| ✍️ **Repurpose content**        | \"Turn this video into a 1,500-word blog post: [URL]\"                                            |\n| 📡 **Monitor a creator**       | \"Each morning, list new uploads from @hubermanlab and tell me which to watch.\"                  |\n| 🏛️ **Build a content database** | \"Pull every video from @veritasium and store title + transcript.\"                              |\n| 🎯 **Competitor analysis**      | \"Search inside @MKBHD for any video about [competitor product] and summarize the takeaways.\"   |\n\n---\n\n## 💳 Pricing & Rate Limits\n\n| Plan                | Price             | Credits      | Rate Limit  |\n| ------------------- | ----------------- | ------------ | ----------- |\n| **Free**            | $0 (one-time)     | 100          | 60 req/min  |\n| **Starter Monthly** | $5/month          | 1,000/month  | 200 req/min |\n| **Starter Annual**  | $54/year ($4.50/mo) | 1,000/month  | 300 req/min |\n\n- **1 Credit** = 1 successful request (HTTP 200)\n- Failed and rate-limited requests do **not** consume credits.\n- `get_channel_latest_videos` is **free** (no credits charged).\n- [View pricing](https://transcriptapi.com/#pricing) · [Manage credits](https://transcriptapi.com/billing)\n\n---\n\n## 🚨 Troubleshooting\n\n<details>\n<summary><b>Authentication errors (401)</b></summary>\n\n- Verify your API key starts with `sk_`\n- Check for extra spaces when copying\n- Ensure the key is active in your [dashboard](https://transcriptapi.com/dashboard/api-keys)\n- If using OAuth, try re-authorizing\n</details>\n\n<details>\n<summary><b>No credits (402)</b></summary>\n\n- Check your credit balance at the [dashboard](https://transcriptapi.com/dashboard)\n- Purchase more credits or upgrade your plan\n</details>\n\n<details>\n<summary><b>Video not available (404)</b></summary>\n\n- The video might not have captions/subtitles enabled\n- The video might be private or age-restricted\n- The video might be region-locked\n</details>\n\n<details>\n<summary><b>Rate limiting (429)</b></summary>\n\n- Respect the `Retry-After` header\n- Implement exponential backoff in your client\n- Upgrade to a paid plan for higher limits\n</details>\n\n<details>\n<summary><b>OAuth issues</b></summary>\n\n- Clear browser cookies and try again\n- For ChatGPT, try switching between Dynamic and Static registration\n- Ensure popup blockers aren't preventing the auth window\n</details>\n\n---\n\n## 🔗 Also available as a REST API\n\nBuilding an app instead of an agent? The same backend ships as a JSON REST API.\n\n|                 | MCP                         | REST API                                                  |\n| --------------- | --------------------------- | --------------------------------------------------------- |\n| **Best for**    | AI assistants & agents      | Apps & backend services                                   |\n| **Setup**       | Add a URL                   | Code integration                                          |\n| **Get started** | This README                 | [API docs →](https://transcriptapi.com/docs/api) · [Swagger →](https://transcriptapi.com/swagger) |\n\nBase URL: `https://transcriptapi.com/api/v2`\n\n---\n\n## 🤝 Connect\n\n- 🌐 **Website:** [transcriptapi.com](https://transcriptapi.com)\n- 📚 **Docs:** [transcriptapi.com/docs](https://transcriptapi.com/docs)\n- 🔧 **API Reference:** [transcriptapi.com/docs/api](https://transcriptapi.com/docs/api)\n- 🤖 **MCP Setup Guides:** [Claude](https://transcriptapi.com/docs/mcp/claude) · [ChatGPT](https://transcriptapi.com/docs/mcp/chatgpt) · [OpenAI Agent Builder](https://transcriptapi.com/docs/mcp/openai-agent-builder)\n- 💬 **Contact:** [transcriptapi.com/contact](https://transcriptapi.com/contact)\n- 📂 **Listed in:** [awesome-agent-plugins](https://github.com/ZeroPointRepo/awesome-agent-plugins), our directory of verified Agent Plugins on the open standard\n\n---\n\n## 📋 MCP Registry\n\nThis server is published to the official [Model Context Protocol Registry](https://registry.modelcontextprotocol.io/) under the name:\n\n```\ncom.transcriptapi/youtube-transcript-and-youtube-search\n```\n\n---\n\n<p align=\"center\">\n  <sub>© 2026 Zero Point Studio d.o.o. · Released under the <a href=\"./LICENSE\">MIT License</a></sub>\n</p>\n",
  "bytes": 25930,
  "sha": "1a6fafb4fd23f4ba75f27baeadb0f7f83f958041db0ec6af0cb5be5aa5852752",
  "repo_slug": "zeropointrepo/youtube-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_transcriptapi_youtube_transcript_and_df40ab3a/readme"
}