Skip to main content
Glama

oratilo-mcp

MCP server for oratilo — a shared library of YouTube videos re-edited into concept-structured summaries.

What it's for: before an agent spends work summarizing a video, it can check whether a summary already exists. A cache is only a cache if something reads it.

Install

Node 18+. No dependencies. Plain MCP over stdio, so any MCP client can run it.

Claude Code

claude mcp add --scope user oratilo -- npx -y oratilo-mcp

Codex CLI — codex mcp add, or in ~/.codex/config.toml:

[mcp_servers.oratilo]
command = "npx"
args = ["-y", "oratilo-mcp"]

Kimi CLI — /mcp-config in the TUI, or in ~/.kimi/mcp.json:

{
  "mcpServers": {
    "oratilo": { "command": "npx", "args": ["-y", "oratilo-mcp"] }
  }
}

Anything else — the JSON block above is the common shape (Claude Desktop, Cursor, Windsurf, Cline …); drop it into that client's MCP config file. If you drive GLM / Z.ai or another model through one of these clients, configure the client, not the model provider.

Verify with /mcp in whichever client you used.

Related MCP server: YouTube Tools MCP Server

What you get

Prompt — summarize. One command for people. Give it a YouTube link; it asks which language you want, looks the video up in oratilo, and hands back the existing summary if there is one. If there isn't, it summarizes the video for you normally.

If your client doesn't support MCP prompts, you won't see this command — that's fine. The server sends the same guidance in its instructions at connect time, so just ask in plain language ("summarize this video: ") and the agent will check the library first.

Tool — oratilo_lookup. Exact check for one video. Returns the full summary plus provenance: source, format, updated, and the model recorded when it was generated. Miss means the library doesn't cover that video.

Tool — oratilo_search. Full-text search over the library when you don't have a URL — by topic, phrase, person or company. Returns ranked matches with page links and snippets; follow up with oratilo_lookup for the full text.

Both tools take an optional lang (ko · en · ja · es; default ko).

Verifying a summary

Claims carry footnote markers [n] that map to a timestamp list at the end of each summary. Deep-link source + &t=<seconds>s to check any single claim against the video itself. oratilo stores no transcripts — a summary is an original re-edit, not a transcription.

Scope and limits

  • Read-only. oratilo is a single-author library today; there is no contribution endpoint, so a miss simply means the video isn't covered.

  • The server talks only to oratilo.com public data. It never contacts YouTube.

  • The corpus is small and deliberately curated — expect misses.

  • Summaries can be wrong. Every page has a correction-report link, and updated changes when a page is revised.

ORATILO_BASE may point the server at a localhost origin for development. Any other host is refused and the server falls back to oratilo.com — otherwise a hostile origin could feed an agent invented text as "oratilo's summary". Responses from a development origin carry a warning and drop the citation guidance.

License

MIT.

Status: oratilo is a personal archive — the library is not indexed and is not accepting contributions. This server still works as a read-only lookup against it.

Available Tools

2 tools
oratilo_lookupA

Check whether oratilo (a shared library of concept-structured video summaries) already has a summary for a specific video, BEFORE spending work summarizing it yourself. Returns the full summary plus provenance metadata on a hit. A miss means the video is not covered — summarize it yourself. Accepts YouTube URLs or video ids (arXiv ids reserved for the future).

Inputs: source (required), lang.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: lookup is for checking a specific video ID/URL for existing coverage, while search is for discovering what content exists by topic when no specific URL is known. The descriptions explicitly clarify when to use each, leaving no ambiguity whatsoever.

    Naming Consistency4/5

    Both tools follow a consistent oratilo_ prefix with a clear verb (lookup, search). The pattern is consistent and predictable, though with only two tools the naming convention is minimally demonstrated.

    Tool Count3/5

    At 2 tools, the surface feels thin for a library with search and retrieval capabilities, though it could be argued these two operations are the core of what's needed. The count is borderline but reasonable given the limited scope described.

    Completeness3/5

    Core read operations (lookup and search) are covered, providing a functional surface. However, there are no write/contribution tools (e.g., adding or updating a summary), so the surface covers only the lookup half of the workflow and leaves the 'summarize it yourself' path entirely to the agent.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      C
      maintenance
      Enables AI agents to search, analyze, and extract insights from YouTube videos including transcripts, visual frames, and benchmarks without requiring API keys. Supports semantic search across playlists, sentiment analysis, and visual content indexing with automatic fallback chains for reliable access.
      41
      179 npm
      36
      MIT