@hasdata/youtube-mcp 1.0.6 → 1.0.8

package/README.md

@@ -7,7 +7,7 @@ A hosted Model Context Protocol (MCP) server that gives Claude, Cursor, Windsurf
 **1,000 free credits every month, no card required**, which is 100 YouTube calls.
 
 ```
-https://mcp.hasdata.com/api/mcp?apis=youtube
+https://mcp.hasdata.com/mcp?apis=youtube
 ```
 
 [![Glama score](https://glama.ai/mcp/servers/HasData/youtube-mcp/badges/score.svg)](https://glama.ai/mcp/servers/HasData/youtube-mcp)
@@ -44,7 +44,7 @@ The server URL is the same for every client. We run it hands-on in Claude Code a
 
 | Field | Value |
 | :--- | :--- |
-| URL | `https://mcp.hasdata.com/api/mcp?apis=youtube` |
+| URL | `https://mcp.hasdata.com/mcp?apis=youtube` |
 | Transport | HTTP, streamable |
 | Auth header | `x-api-key: HASDATA_API_KEY` |
 
@@ -54,7 +54,7 @@ Clients with OAuth support can add the same URL as a connector and sign in witho
 <summary><b>Claude Code</b></summary>
 
 ```bash
-claude mcp add --transport http youtube "https://mcp.hasdata.com/api/mcp?apis=youtube" \
+claude mcp add --transport http youtube "https://mcp.hasdata.com/mcp?apis=youtube" \
   --header "x-api-key: HASDATA_API_KEY"
 ```
 
@@ -63,7 +63,7 @@ claude mcp add --transport http youtube "https://mcp.hasdata.com/api/mcp?apis=yo
 <details>
 <summary><b>Claude Desktop</b></summary>
 
-Settings, then Connectors, then Add custom connector, then paste `https://mcp.hasdata.com/api/mcp?apis=youtube` and sign in.
+Settings, then Connectors, then Add custom connector, then paste `https://mcp.hasdata.com/mcp?apis=youtube` and sign in.
 
 For the config-file route, Claude Desktop loads only local (stdio) servers, so it reaches a remote server through a stdio launcher. The `@hasdata/youtube-mcp` package is that launcher, and it reads the key from the environment. Add this to `claude_desktop_config.json`:
 
@@ -104,7 +104,7 @@ Python instead of Node? Swap the launcher for the PyPI package, which `uvx` runs
 {
   "mcpServers": {
     "youtube": {
-      "url": "https://mcp.hasdata.com/api/mcp?apis=youtube",
+      "url": "https://mcp.hasdata.com/mcp?apis=youtube",
       "headers": { "x-api-key": "HASDATA_API_KEY" }
     }
   }
@@ -122,7 +122,7 @@ Python instead of Node? Swap the launcher for the PyPI package, which `uvx` runs
 {
   "mcpServers": {
     "youtube": {
-      "serverUrl": "https://mcp.hasdata.com/api/mcp?apis=youtube",
+      "serverUrl": "https://mcp.hasdata.com/mcp?apis=youtube",
       "headers": { "x-api-key": "HASDATA_API_KEY" }
     }
   }
@@ -138,7 +138,7 @@ Python instead of Node? Swap the launcher for the PyPI package, which `uvx` runs
 {
   "mcpServers": {
     "youtube": {
-      "url": "https://mcp.hasdata.com/api/mcp?apis=youtube",
+      "url": "https://mcp.hasdata.com/mcp?apis=youtube",
       "type": "streamableHttp",
       "headers": { "x-api-key": "HASDATA_API_KEY" },
       "disabled": false
@@ -159,7 +159,7 @@ Python instead of Node? Swap the launcher for the PyPI package, which `uvx` runs
   "servers": {
     "youtube": {
       "type": "http",
-      "url": "https://mcp.hasdata.com/api/mcp?apis=youtube",
+      "url": "https://mcp.hasdata.com/mcp?apis=youtube",
       "headers": { "x-api-key": "HASDATA_API_KEY" }
     }
   }
@@ -175,7 +175,7 @@ Python instead of Node? Swap the launcher for the PyPI package, which `uvx` runs
 
 ```toml
 [mcp_servers.youtube]
-url = "https://mcp.hasdata.com/api/mcp?apis=youtube"
+url = "https://mcp.hasdata.com/mcp?apis=youtube"
 
 [mcp_servers.youtube.headers]
 "x-api-key" = "HASDATA_API_KEY"
@@ -192,7 +192,7 @@ url = "https://mcp.hasdata.com/api/mcp?apis=youtube"
 {
   "mcpServers": {
     "youtube": {
-      "httpUrl": "https://mcp.hasdata.com/api/mcp?apis=youtube",
+      "httpUrl": "https://mcp.hasdata.com/mcp?apis=youtube",
       "headers": { "x-api-key": "HASDATA_API_KEY" }
     }
   }
@@ -227,10 +227,17 @@ Prompts, not code. Paste one in and the agent picks the tool itself. Each is ann
 
 Search takes YouTube's own filter tokens, and an agent narrows by duration, upload date and content type without post-processing. Transcripts arrive with the list of available language tracks, which lets the agent pick one without guessing.
 
-Paging costs a call each time. A research prompt that searches, pages twice, then pulls three transcripts is six calls and 60 credits. The trial goes further on narrow questions than on open-ended crawls.
+Paging costs a call each time. A research prompt that searches, pages twice, then pulls three transcripts is six calls and 60 credits. The free tier goes further on narrow questions than on open-ended crawls.
 
 ## Tools
 
+| Tool | What it returns |
+| --- | --- |
+| `hasdata_youtube_channel_getYoutubeChannel` | Channel identity (title, description, avatar, banner, country, join date), subscriber and total-view counts, social links, and the items on the requested tab (videos…. 10 credits a call |
+| `hasdata_youtube_search_getYoutubeSearchResults` | Searches YouTube for a query and returns the full results page split into `videoResults` (videoId, title, views, length, publish date, chapters, channel info, extensions…. 10 credits a call |
+| `hasdata_youtube_transcript_getYoutubeTranscript` | The timed transcript (subtitles) of a YouTube video by its 11-character `videoId`. 10 credits a call |
+| `hasdata_youtube_video_getYoutubeVideo` | Title, thumbnail, raw + normalized views and likes, `lengthSeconds`, publish date, category, keywords/tags, `isFamilySafe` / `isUnlisted` flags, the uploading channel…. 10 credits a call |
+
 Four tools, all read-only. Samples below are trimmed from real calls, and the numbers in them move as YouTube updates. Read them as shapes. Each tool name links to its endpoint reference, which carries the full field list.
 
 The samples are the payload, not the whole response. A `tools/call` result carries one text block, and that text is itself JSON holding `url`, `status`, `text` and `json`, with the scraped data under `json`. From a raw JSON-RPC response the path is `result.content[0].text`, parsed, then `.json`. A chat client unwraps that for you and code talking to the endpoint directly does not.
@@ -387,9 +394,9 @@ Every YouTube tool costs **10 credits per successful call**. Response size does
 
 The free tier is **1,000 credits every month with no card**, which is 100 YouTube calls. It renews with the billing cycle, so a low-volume agent runs on the free tier indefinitely.
 
-Paid plans start at **$49 a month** for 200,000 credits, which is 20,000 calls. The unit price falls with volume, from **$2.45 per 1,000 calls** on the entry plan to **$0.99** on Business, **$0.83** on Growth and **$0.75** on the largest [high-volume plans](https://hasdata.com/prices?utm_source=github&utm_medium=syndication&utm_campaign=youtube-mcp).
+Paid plans start at **$59 a month** for 200,000 credits, which is 20,000 calls. The unit price falls with volume, from **$2.95 per 1,000 calls** on the entry plan to **$1.19** on Basic and **$0.83** across the Growth tiers. Current figures live on the [pricing page](https://hasdata.com/prices?utm_source=github&utm_medium=syndication&utm_campaign=youtube-mcp).
 
-Your plan also sets concurrency. The free tier allows 1 request at a time, Startup 15, Business 30, Growth 50, and the high-volume plans run from 200 to 1,500. Handle the overflow case defensively in anything unattended, because an agent that fans out will reach the ceiling before you do.
+Your plan also sets concurrency. The free tier allows 1 request at a time, Startup 5, Basic 15, and the Growth tiers run from 50 to 500. Handle the overflow case defensively in anything unattended, because an agent that fans out will reach the ceiling before you do.
 
 A request that comes back non-200 is not billed. A successful call that finds nothing is still a call.
 
@@ -416,7 +423,7 @@ Against the official **YouTube Data API v3**:
 | Transcripts of videos you do not own | `captions.download` "requires the user to have permission to edit the video", per [Google's reference](https://developers.google.com/youtube/v3/docs/captions/download) | Yes, with the language list |
 | Chapters in search results | No | Yes |
 | Views and likes in search results | Absent, and a second `videos.list` call returns them as strings | Display string and integer in the same response |
-| Cost | Free inside the daily quota | Paid past the trial, 10 credits a call |
+| Cost | Free inside the daily quota | Paid past the free tier, 10 credits a call |
 | Writes and private data | Uploads, playlists, comments and your own analytics over OAuth | Read-only, public data only |
 
 The last two rows matter. If the daily quota covers your volume and you own the channel you are querying, the official API is the cheaper answer and you should take it.

package/index.mjs

@@ -6,7 +6,7 @@ import { spawn } from 'node:child_process';
 import { createRequire } from 'node:module';
 import { dirname, join } from 'node:path';
 
-const URL = 'https://mcp.hasdata.com/api/mcp?apis=youtube';
+const URL = 'https://mcp.hasdata.com/mcp?apis=youtube';
 const key = process.env.HASDATA_API_KEY;
 if (!key) {
   process.stderr.write('HASDATA_API_KEY is not set. Create a free key at https://app.hasdata.com and set HASDATA_API_KEY.\n');

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@hasdata/youtube-mcp",
   "mcpName": "com.hasdata/youtube",
-  "version": "1.0.6",
+  "version": "1.0.8",
   "description": "MCP server for YouTube data (search, video, channel, transcript) through HasData's hosted API. No Google Cloud project, no YouTube Data API key. 1,000 free credits every month.",
   "type": "module",
   "bin": {