Arcmira: YouTube Transcript Search vs Scribefy MCP
In-depth architectural comparison of the Arcmira: YouTube Transcript Search and Scribefy MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Arcmira: YouTube Transcript Search
Search & Data Extraction · Remote HTTP/SSE
Quality: 81/100 (Excellent) | Auth: OAuth 2.0
Scribefy MCP
Search & Data Extraction · Local stdio
Quality: 59/100 (Good) | Auth: API Key required
Verdict Summary: Choose Arcmira: YouTube Transcript Search if you need specialized Search & Data Extraction tools running via a hosted cloud SSE transport. Choose Scribefy MCP if your workspace requires Search & Data Extraction integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Arcmira: YouTube Transcript Search when:
You need dedicated capabilities in the Search & Data Extraction domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: OAuth 2.0 (Freemium).
The arcmira client reference: the id rule, which method answers which question, every method with arguments and return fields, nine worked example programs, the quirks that cost answers, the budget and monitor rules, error codes, and doc links. About 24,000 characters; `topic` narrows it to one met…
arcmira_execute_read
What the program printed plus its return value. The code is the body of an async function with `arcmira` and `ArcmiraError` in scope. Reads, Premium transcripts included, and the user's monitors. Limits: 30 seconds, 40 API calls, and 12,000 characters of output in total, 3,000 per string, and 100 i…
arcmira_execute_write
The same as `arcmira_execute_read`, with the account writes added: `arcmira.monitors.create`, `arcmira.monitors.update` (including `paused`), `arcmira.monitors.addEntities`, `arcmira.monitors.addName` and `arcmira.monitors.attachTrackers`. Nothing is deleted.
arcmira_feedback
One `POST /v1/feedback` of type `experience`. `category` is `wrong_entity`, `bad_data`, `missing`, `slow`, `confusing` or `other`; `note` says what happened. Returns the feedback id.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Arcmira: YouTube Transcript Search is categorized under Search & Data Extraction and uses a remote streaming HTTP/SSE transport. In contrast, Scribefy MCP belongs to Search & Data Extraction using local stdio subprocess. Select Arcmira: YouTube Transcript Search when you need capabilities focused on search & data extraction and Scribefy MCP when you require tools for search & data extraction.
Pulls the transcript of a YouTube video and returns it as Markdown with timestamps. Use this whenever the user provides a YouTube URL and wants to summarise, quote, search, or otherwise process the video's spoken content.
Costs credits on first fetch (1 credit ≤15min, 2 credits 15–45min, 4 credits 45min–2h, 8 credits 2h+). Cached extractions are free — videos other Scribefy users have already extracted are cached for 30 days.
Returns the title, channel, duration, language, and the transcript itself split into segments with clickable timestamps.
search_videos
Search YouTube for videos matching a query string. Returns up to `limit` results (default 10, max 25) with title, channel, duration, view count, and URL. Free — no credits charged. Use this when the user asks 'find me videos about X' before chaining into extract_transcript on a specific result.
get_video_metadata
Look up title, channel, duration, view count, upload date, and available caption tracks for a video. Does NOT pull the transcript — use extract_transcript for that. Free — no credits charged. Useful to inspect a video before deciding whether to extract, or to discover which caption languages are available.
get_related_videos
Return the videos YouTube recommends after a given video — the 'Up next' / 'Related' feed. Returns up to `limit` results (default 10, max 25). Free — no credits charged. Use this to expand research from a single starting video, or to find adjacent content.
Give your AI the ability to find who said what with timestamps, discover what’s being discussed across videos and livestreams, and distinguish organic recommendations from sponsored ad reads. Search indexed YouTube transcripts for quotes, speaker appearances, mentions, sponsors and recommendations. API docs: https://arcmira.com/docs. Coverage and account access vary; speaker and sponsorship classifications can be incomplete or incorrect, so check the linked source. The hosted MCP exposes arcmira_describe, arcmira_execute_read, arcmira_execute_write and arcmira_feedback. Connect with Arcmira OAuth or a personal bearer API key. A paid read uses credits from your plan, then your on-demand budget. Setup: https://arcmira.com/docs/mcp-server. Usage: https://arcmira.com/docs/usage-and-billing. Public plugin files are Apache-2.0; the hosted research service is proprietary.
Extract timestamped YouTube transcripts, plus search, video metadata, and related-video tools for Claude, Cursor, Windsurf, and AI agents.