How to connect
Same URL, five paste targets. Ready surface · Auth required. Not a safe-to-install badge. Handshake this URL
Paste into Settings → MCP or .cursor/mcp.json.
{
"mcpServers": {
"alberduris-summiz": {
"url": "https://summiz--alberduris.run.tools"
}
}
}
Paste into .vscode/mcp.json.
{
"mcpServers": {
"alberduris-summiz": {
"url": "https://summiz--alberduris.run.tools"
}
}
}
Settings → Connectors → Add → Custom → Web. Paste the URL. Enable in a new chat.
Claude → Settings → Connectors → Add → Custom → Web
Name: Summiz
URL: https://summiz--alberduris.run.tools
OAuth only if this server requires it.
Save, start a new chat, enable the connector.
Developer mode custom connector. ChatGPT cannot reach localhost.
Settings → Apps & Connectors → Advanced → Developer mode ON
Create custom connector
Name: Summiz
MCP server URL: https://summiz--alberduris.run.tools
Auth: none unless the server requires OAuth
New chat → + → Developer mode → enable the connector
Register the HTTPS URL, then claude mcp list.
claude mcp add --transport http alberduris-summiz \
https://summiz--alberduris.run.tools
Pass on session/new as mcpServers when the agent advertised HTTP MCP.
[
{
"type": "http",
"name": "alberduris-summiz",
"url": "https://summiz--alberduris.run.tools"
}
]
Paste into a README or docs site. The widget loads snippets from Influzer — still not a SAFE badge.
Same handshake clock as this listing (overlay / warm / seed; live tools/list only if that is missing). Indigo is live_ok, amber is auth_required, gray is unreachable. Not a SAFE badge. Stdio listings have no badge.
[](https://www.influzer.ai/mcp/probe?url=https%3A%2F%2Fsummiz--alberduris.run.tools)
<div data-influzer-install="alberduris-summiz"></div>
<script async src="https://www.influzer.ai/embed/install.js"></script>
https://www.influzer.ai/embed/mcp/alberduris-summiz.md
JSON: https://www.influzer.ai/api/v1/install/alberduris-summiz
Recipes using this server
No published recipes yet for this server.
Listing quality
Observable facts from our catalog and daily probe — not a safe-to-install badge.
- Surface
- Ready surface
- Auth gate
- Auth gate
- Tools source
- tools/list (live)
Observable catalog + probe facts — not a safe-to-install badge. How we verify.
Verification summary
Stored signals only. Not a safety score.
- Verification grade
- A (85)
- Last verified
- Status
- Auth required
- Response time
- 569 ms
- Auth
- Auth gate
- Transport
- http, HTTPS
- Tools indexed
- 13
Probe history
- · auth_required · 569 ms
- · auth_required · 573 ms
Tools
(13)-
search-contentSearch the Summiz content catalog. Returns videos and podcasts matching the query. IMPORTANT: Use SHORT keywords (1-2 words max) separated by commas. Each keyword segment should be a BIGRAM at most. Examples: 'tomato pruning, organic fertilizer' or 'container gardening' NOT 'how to grow tomatoes in containers at home'. Defaults to the public catalog; set scope='library' to search only the user's own saved library, which requires a connected Summiz account.
-
search-youtube-videosSearch YouTube videos by keywords to obtain videoId and URL, optionally inside one channel. Each video comes with its channel (channelId, channelHandle), upload date, duration, whether it is a Short, aspect ratio, views, likes, comments and a thumbnail URL, so you can pick one without opening it. channelQuery is a filter, not a keyword: a handle (@polymatter), channel URL, channel ID or video URL picks that channel; a plain name works only when one channel clearly carries it, otherwise the call
-
resolve-youtube-channelFind the YouTube channel behind a name, handle or URL, with its channelId, handle, subscribers and video count. A handle (@polymatter), channel URL, channel ID or video URL names exactly one channel. A plain name resolves when one channel clearly carries it (status 'resolved', with the other matches in alternatives); otherwise status is 'ambiguous' and candidates lists the channels it could mean, the ones carrying that exact name first. Never returns videos. Pass the handle on to list-youtube-ch
-
list-youtube-channel-videosList the videos one or more YouTube channels uploaded themselves: never re-uploads, reactions or other channels' videos. Up to 10 channels per call, each answered under the string you passed for it. Choose long-form videos or Shorts (tab), newest or most viewed first (sort), and optionally a publication window (since, until). Without a window, 'popular' ranks the channel's 200 most viewed; with one, it ranks the videos published in that window. Each video carries the same metadata as search-yout
-
get-quick-takesFetch Quick Takes for a specific piece of content. Quick Takes help users decide if content is worth their time. Accepts either a Summiz UID (from search-content or inferred from a Summiz URL) or a YouTube video ID. `externalId` is interpreted as a YouTube video ID; for content from any other origin, use `uid`. Prioritizes UID if both provided.
-
get-summaryFetch full Summary for a specific piece of content. Returns comprehensive summary with TLDR, golden nuggets, sections, and conclusion. Accepts either a Summiz UID (from search-content) or a YouTube video ID. `externalId` is interpreted as a YouTube video ID; for content from any other origin, use `uid`. Prioritizes UID if both provided.
-
get-notesFetch Study Notes for a specific piece of content. Notes are the study-grade view of a video, distinct from a Summary: an overview, thematic sections split into individual concepts (each with an 'in other words' restatement), a glossary of key terms, and review questions tagged recall / conceptual / application for self-testing. Accepts either a Summiz UID (from search-content or create-notes) or a YouTube video ID. `externalId` is interpreted as a YouTube video ID; for content from any other or
-
get-transcriptFetch the full transcript of a video or podcast (the complete text, not an excerpt). Useful when the user asks about details of the source that the Quick Takes or Summary do not cover. Accepts a Summiz UID (from search-content) or an external ID (e.g., a YouTube video ID from the URL); if both are provided, the UID takes priority. If the video is not in Summiz yet, provide youtubeUrl: the transcript is fetched and the video is added to Summiz.
-
create-summaryTo create a Full Summary, users must do so from Summiz.ai with an account. This tool automatically generates Quick Takes (free, no account required) and checks if Summary content exists. Returns available content and the digest URL for accessing or generating Summary content.
-
create-quick-takesCreate Quick Takes for a YouTube video that is not on Summiz yet. Generation typically completes within 3 minutes.
-
create-notesCreate Study Notes for a YouTube video — the study-grade companion to a summary. Where a Summary condenses a video into TLDR, golden nuggets and prose sections, Notes restructures it for LEARNING: an overview, thematic sections broken into individual concepts (each with a plain-language 'in other words' restatement), a glossary of key terms, and recall/conceptual/application review questions to self-test with. Free and no account required. Generation is progressive — the phases (sections, glossa
-
list-digestsList digests without a search query. The default 'catalog' scope returns the most recent public Summiz digests (newest first) for a language. Set scope='library' to list the user's own saved digests, most recently added first — this requires a connected Summiz account. The 'language' parameter applies to the catalog only; library results come back in each item's saved language.
-
clickbait-defenderAudits the deal between a video's packaging and what its transcript actually pays. A YouTube URL accompanied by 'CD' (shorthand for Clickbait Defender) is a request for this tool. Returns the questions the title and thumbnail made you click on, each answered from the transcript, plus an honesty score (100 = every promise paid in full, 0 = the promise goes entirely unpaid or the video's own content refutes it), timestamped signal peaks, and a watch-if line. Creating the report takes ~20-60 second
Tool source: tools/list (live) · last probed 2026-11-10