MCP Server Documentation

Setup

Pick your platform and copy the config. The remote server requires no installation — just paste the config and restart.

Step 1 — Open MCP settings

Open Cursor → Settings → MCP → + Add new MCP server

Step 2 — Paste this config

{
  "mcpServers": {
    "algrow": {
      "url": "https://mcp.algrow.online/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key-here"
      }
    }
  }
}

No installation needed. This connects directly to Algrow's hosted MCP server. Just paste, replace your API key, and restart Cursor.

Step 1 — Open Connectors settings

Go to claude.ai → Settings → Connectors → Add custom connector

Step 2 — Enter these details

Name: Algrow

Server URL: https://mcp.algrow.online/mcp

Client ID: algrow_mcp_claude

Client Secret: zoJFY044Ih2GKhkf3ae25DwFqupsjoPS54Ic0A3ZAaZEsR7I4EAftEncqCIHLN-7

Step 3 — Authorize your account

After adding the connector, Claude will redirect you to sign in with your Algrow account. Click Approve to connect.

No API key needed. Claude.ai uses OAuth to connect directly to your Algrow account. Works on web and mobile — your tools sync across all devices.

Installation Demo

Step 1 — Enable Developer Mode

Go to chatgpt.com → Settings → Apps → Advanced settings → toggle on Developer mode

Requires a ChatGPT Plus, Pro, Business, or Enterprise plan.

Step 2 — Add custom tool

Go to Settings → Apps → Create App

Step 3 — Enter these details

Name: Algrow

MCP Server URL: https://mcp.algrow.online/mcp

Authentication: OAuth

Step 4 — Confirm and authorize

Tick "I understand and want to continue", then click Create. ChatGPT will auto-discover the OAuth settings — no Client ID or secret needed.

When you first use an Algrow tool, ChatGPT will redirect you to sign in with your Algrow account. Click Approve to connect.

No API key needed. ChatGPT uses OAuth to connect directly to your Algrow account. You can use the same Algrow account across both ChatGPT and Claude — each gets its own connection.

Run this command in your terminal

claude mcp add algrow --transport http https://mcp.algrow.online/mcp --header "Authorization: Bearer your-api-key-here"

That's it. Claude Code will connect to Algrow automatically. Run /mcp to verify the server is connected.

Step 1 — Open MCP settings

Open VS Code → Ctrl+Shift+P (or Cmd+Shift+P) → type "MCP: Add Server"

Step 2 — Or add to .vscode/mcp.json in your project

{
  "servers": {
    "algrow": {
      "type": "http",
      "url": "https://mcp.algrow.online/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key-here"
      }
    }
  }
}

Requires GitHub Copilot. MCP support in VS Code works through GitHub Copilot's agent mode. Make sure you have the Copilot extension installed and updated.

Add to your Windsurf MCP config

Open Windsurf → Settings → MCP → Add Server, or edit the config file directly:

{
  "mcpServers": {
    "algrow": {
      "serverUrl": "https://mcp.algrow.online/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key-here"
      }
    }
  }
}

Config file location:
• macOS / Linux: ~/.codeium/windsurf/mcp_config.json
• Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

After saving, restart Windsurf.

Step 1 — Open your Codex config

Open or create ~/.codex/config.toml (or .codex/config.toml in your project root)

Step 2 — Add the Algrow MCP server

[mcp_servers.algrow] url = "https://mcp.algrow.online/mcp" http_headers = { "Authorization" = "Bearer your-api-key-here" }

No installation needed. Codex connects directly via Streamable HTTP. After saving, restart Codex to connect.

Generic MCP configuration

Any MCP-compatible client can connect using the Streamable HTTP endpoint:

Server URL:  https://mcp.algrow.online/mcp
Transport:   Streamable HTTP
Auth header: Authorization: Bearer your-api-key-here

Works with any MCP client that supports Streamable HTTP transport — including Cline, Continue, Zed, Amazon Q Developer, and others. Check your client's docs for where to add MCP server configurations.

Replace your-api-key-here with your actual API key from Settings. After configuring, restart your client to connect.

What is MCP?

The Model Context Protocol (MCP) lets AI assistants use external tools. The Algrow MCP server gives your AI assistant direct access to Algrow's YouTube intelligence — search channels, find viral videos, scrape YouTube data, and generate TTS audio through natural conversation.

1

Get your API key

Grab your key from Settings

2

Pick your platform

Add the config to Cursor, Claude, VS Code, or Windsurf

3

Start asking

"Find me roblox Shorts channels under 50k subs growing fast"

Channel Search

Search Algrow's database of YouTube Shorts and Longform channels with similarity search, keyword matching, and advanced filters.

TOOL search_shorts_channels

Search Shorts channels with similarity search, keyword matching, and advanced filters. Returns channel metadata, growth metrics, and recent videos.

Example prompt

"Search for 'roblox' Shorts channels in English under 50k subs that gained over 100k views in the last 24 hours"

Parameter	Type	Default	Description
q	string	required	Search query. Accepts a channel ID, `@handle`, channel URL, a video URL (e.g. `https://youtube.com/shorts/...`, `https://youtu.be/...`), or topic keywords. Comma-separated for multiple, prefix with `-` to exclude.
sort	string	null	Sort: `{field}_{asc\|desc}`. Fields: `subs`, `views`, `videos`, `age`, `added`, `views_24h`, `subs_24h`, `views_48h`, `similarity`. Defaults to `similarity` when searching.
page	integer	1	Page number (1-indexed, max 20)
min_subs	integer	null	Minimum subscriber count
max_subs	integer	null	Maximum subscriber count
min_avg_views	integer	null	Minimum average views per video
max_avg_views	integer	null	Maximum average views per video
min_age	integer	null	Minimum channel age in days since first upload
max_age	integer	null	Maximum channel age in days since first upload
min_uploads	integer	null	Minimum number of videos
max_uploads	integer	null	Maximum number of videos
min_views	integer	null	Minimum total view count
max_views	integer	null	Maximum total view count
min_views_24h	integer	null	Minimum views gained in last 24 hours
max_views_24h	integer	null	Maximum views gained in last 24 hours
min_views_48h	integer	null	Minimum views gained in last 48 hours
max_views_48h	integer	null	Maximum views gained in last 48 hours
min_days_added	integer	null	Minimum days since channel was added to Algrow's database (NOT channel age)
max_days_added	integer	null	Maximum days since channel was added to Algrow's database (NOT channel age)

TOOL search_longform_channels

Search Longform channels with similarity search, keyword matching, and advanced filters. Returns channel metadata, growth metrics, monetization status, and recent videos with duration.

Example prompt

"Search for 'top 10 unsolved mysteries' monetized English longform channels under 100k subs with at least 10k average views, sorted by newest"

Parameter	Type	Default	Description
q	string	required	Search query. Accepts a channel ID, `@handle`, channel URL, a video URL (e.g. `https://youtube.com/shorts/...`, `https://youtu.be/...`), or topic keywords. Comma-separated for multiple, prefix with `-` to exclude.
sort	string	null	Sort: `{field}_{asc\|desc}`. Fields: `subs`, `views`, `videos`, `age`, `total_views`, `added`, `views_24h`, `subs_24h`, `views_48h`, `similarity`. Defaults to `similarity` when searching.
page	integer	1	Page number (1-indexed, max 20)
min_subs	integer	null	Minimum subscriber count
max_subs	integer	null	Maximum subscriber count
min_avg_views	integer	null	Minimum average views per video
max_avg_views	integer	null	Maximum average views per video
min_age	integer	null	Minimum channel age in days since first upload
max_age	integer	null	Maximum channel age in days since first upload
min_uploads	integer	null	Minimum number of videos
max_uploads	integer	null	Maximum number of videos
min_duration	integer	null	Minimum average video duration in seconds
max_duration	integer	null	Maximum average video duration in seconds
monetized	string	null	Filter by monetization: `yes` or `no`
min_views_24h	integer	null	Minimum views gained in last 24 hours
max_views_24h	integer	null	Maximum views gained in last 24 hours
min_views_48h	integer	null	Minimum views gained in last 48 hours
max_views_48h	integer	null	Maximum views gained in last 48 hours
min_days_added	integer	null	Minimum days since channel was added to Algrow's database (NOT channel age)
max_days_added	integer	null	Maximum days since channel was added to Algrow's database (NOT channel age)

TOOL youtube_search

Search everything on YouTube in one call — videos, channels, and playlists all in the same result list. Sort by relevance, views, upload date, or rating. Narrow by duration, upload recency, or a custom “last N days” window.

Example prompt

"Find the most-viewed 'rise and fall' videos posted in the last 3 days"

Parameter	Type	Default	Description
query	string	required	Search query.
type	string	all	`all`, `video`, `channel`, `playlist`, `movie`.
sort_by	string	relevance	`relevance`, `view_count`, `upload_date`, `rating`.
upload_date	string	all	`all`, `hour`, `today`, `week`, `month`, `year`.
duration	string	all	`short` (<4m), `medium` (4–20m), `long` (>20m). Videos only.
published_within_days	integer	null	Narrow video results to those posted within the last N days. Finer than `upload_date` — use for "last 3 days" phrasings.
limit	integer	30	Max results (1–100).

Channel Data

Look up rich metadata for any YouTube channel by ID. If you only have a @handle or URL, call resolve_handle or resolve_url first.

TOOL get_channel_about

Pull everything from a channel's About page in one call — name, description, subscriber and view counts, country, language, join date, topics, social links, trailer, banner, and more.

Example prompt

"Give me the full About page for The Geo Network"

Parameter	Type	Default	Description
channel_id	string	required	24-char YouTube channel ID (starts with `UC`).

TOOL get_channel_daily_analytics

See how a channel has grown day-by-day across any date range you pick — subscribers, views, and uploads, plus a summary with total growth over the window.

Example prompt

"How many subs did The Geo Network gain in the last 30 days?"

Parameter	Type	Default	Description
channel_id	string	required	24-char YouTube channel ID.
start_date	string	30 days ago	ISO `YYYY-MM-DD`.
end_date	string	today	ISO `YYYY-MM-DD`. Max window 365 days.

TOOL get_channel_videos

Browse a channel's longform uploads, newest first — with titles, view counts, durations, upload dates, and thumbnails.

Example prompt

"Show me the 20 most recent longform videos from MrBeast"

Parameter	Type	Default	Description
channel_id	string	required	24-char YouTube channel ID.
limit	integer	30	Max videos (1–100).

TOOL get_channel_shorts

Browse a channel's Shorts, newest first — the real Shorts tab, not short-duration regular videos.

Example prompt

"What are the recent Shorts from this channel?"

Parameter	Type	Default	Description
channel_id	string	required	24-char YouTube channel ID.
limit	integer	30	Max shorts (1–100).

TOOL get_channel_playlists

See every public playlist on a channel — title, description, video count, and thumbnail for each. Paginates in batches of 50.

Example prompt

"Show me every playlist this channel has"

Parameter	Type	Default	Description
channel_id	string	required	24-char YouTube channel ID.
page_token	string	null	Pass `next_page_token` from a previous response for subsequent pages.

Terminated Channels

TOOL search_terminated_channels

Search terminated/deleted YouTube channels. Returns channel metadata, growth metrics at time of termination, and top videos. Available on all plans.

Example prompt

"Search for terminated 'roblox' channels that had over 100k subscribers"

Parameter	Type	Default	Description
q	string	required	Search query. Matches channel titles and video titles. Comma-separated for multiple keywords.
languages	string	null	Filter by language. Comma-separated.
sort	string	date_desc	Sort: `{field}_{asc\|desc}`. Fields: `subs`, `views`, `videos`, `age`, `views_24h`, `subs_24h`, `views_48h`, `date`, `similarity`
page	integer	1	Page number (1-indexed, max 20)
per_page	integer	50	Results per page (max 50)
min_subs	integer	null	Minimum subscriber count
max_subs	integer	null	Maximum subscriber count
min_views	integer	null	Minimum total view count
max_views	integer	null	Maximum total view count
min_avg_views	integer	null	Minimum average views per video
max_avg_views	integer	null	Maximum average views per video
min_age	integer	null	Minimum channel age in days
max_age	integer	null	Maximum channel age in days
min_uploads	integer	null	Minimum number of videos
max_uploads	integer	null	Maximum number of videos
monetized	string	null	Filter by monetization: `yes` or `no`

Viral Videos

TOOL search_viral_videos

Find viral videos — by similarity to a query/video, or by pure filters. Three modes: (1) pass search for a topic/channel query, (2) pass video_url to find similar videos, (3) omit both and browse by filters alone (e.g. “biggest outliers from the last 7 days with 100k+ views”). To check if specific channels have viral videos, pass their channel_ids from a prior search. Filter by video views, channel size, growth metrics, upload recency, language, and outlier score (a video's views ÷ its channel's average views per video — e.g. 3.2 means the video got 3.2× the channel's typical views). Each result includes an outlier_score field; sort by outlier_score to surface the biggest over-performers.

Example prompt

"Find viral Shorts videos about cooking uploaded in the last 7 days with over 1 million views"

Parameter	Type	Default	Description
search	string	null	Text search query — uses title similarity matching. Pass exact video titles, not paraphrased keywords. Optional — omit along with `video_url` to browse by filters alone.
video_url	string	null	YouTube video URL (watch, shorts, or youtu.be link). Finds similar videos based on the given video. Optional.
content_type	string	shorts	Content type: `shorts` or `longform`
channel_ids	string	null	Comma-separated channel IDs to filter by (e.g. from a prior `search_shorts_channels` result). When provided, only returns viral videos from these specific channels.
languages	string	English	Filter by language. Comma-separated.
sort_by	string	similarity	Sort: `similarity` (default, best for finding most relevant videos — requires `search` or `video_url`; auto-swaps to `outlier_score` for pure-filter browsing), `views` (most viewed), `recent` (newest fetched), `upload_date` (newest uploaded), `outlier_score` (biggest over-performers — views vs channel average)
page	integer	1	Page number (1-indexed, max 20)
per_page	integer	50	Results per page (max 50)
min_video_views	integer	25000	Minimum video view count. Default matches the system's natural floor.
max_video_views	integer	null	Maximum video view count
min_subs	integer	null	Minimum channel subscriber count
max_subs	integer	null	Maximum channel subscriber count
min_uploads	integer	null	Minimum channel video count
max_uploads	integer	null	Maximum channel video count
min_channel_age	integer	null	Minimum channel age in days
max_channel_age	integer	null	Maximum channel age in days
uploaded_within_days	integer	null	Only include videos uploaded within this many days. E.g. `7` = last week, `30` = last month.
uploaded_before_days	integer	null	Exclude videos newer than this many days ago. E.g. `7` = only show videos older than 1 week.
min_duration	integer	null	Minimum video duration in seconds (longform only)
max_duration	integer	null	Maximum video duration in seconds (longform only)
min_views_24h	integer	null	Minimum channel views gained in last 24h (shorts only)
max_views_24h	integer	null	Maximum channel views gained in last 24h (shorts only)
min_views_48h	integer	null	Minimum channel views gained in last 48h (shorts only)
max_views_48h	integer	null	Maximum channel views gained in last 48h (shorts only)
min_outlier_score	float	null	Minimum outlier score. A video's `outlier_score` = its view count ÷ its channel's average views per video, so `2.5` means “video got 2.5× the channel's typical views.” Use this to surface videos over-performing their channel.
max_outlier_score	float	null	Maximum outlier score. Rarely needed — usually pair with `min_outlier_score`.
min_similarity	integer	null	Minimum similarity score (0–100). Only return videos with at least this similarity %. E.g. `55` = only show videos that are 55%+ similar.

Thumbnail Search

TOOL search_by_thumbnail

Search for longform videos by thumbnail similarity. Provide a YouTube video URL, an image URL, or a text description to find videos with visually similar thumbnails using similarity matching.

Example prompts

"Find videos with thumbnails similar to this image: https://i.ytimg.com/vi/abc123/maxresdefault.jpg"

"Search for thumbnails that show a before and after transformation"

Parameter	Type	Default	Description
image_url	string	null	URL of a thumbnail image to search with. Supports JPEG, PNG, WebP, and GIF.
video_url	string	null	YouTube video URL. Accepts watch, shorts, and youtu.be links.
q	string	null	Text description of the thumbnail style (e.g. “red arrow pointing at shocked face”).
limit	integer	50	Max results to return (1–50)
min_similarity	float	0.3	Minimum similarity threshold (0–1). Higher values return fewer but more visually similar results.
min_views	integer	null	Minimum video view count filter
max_views	integer	null	Maximum video view count filter
uploaded_within_days	integer	null	Only include videos uploaded within this many days. E.g. `7` = last week, `30` = last month.
uploaded_before_days	integer	null	Exclude videos newer than this many days ago. E.g. `7` = only show videos older than 1 week.

TOOL search_terminated_by_thumbnail

Search terminated/deleted channel videos by thumbnail similarity. Same as search_by_thumbnail but searches the terminated channels archive instead of active longform channels.

Example prompts

"Find terminated channel videos with thumbnails similar to this image: https://i.ytimg.com/vi/abc123/maxresdefault.jpg"

"Search terminated channels for thumbnails that show clickbait red arrows"

Parameter	Type	Default	Description
image_url	string	null	URL of a thumbnail image to search with. Supports JPEG, PNG, WebP, and GIF.
video_url	string	null	YouTube video URL. Accepts watch, shorts, and youtu.be links.
q	string	null	Text description of the thumbnail style (e.g. “red arrow pointing at shocked face”).
limit	integer	50	Max results to return (1–50)
min_similarity	float	0.3	Minimum similarity threshold (0–1). Higher values return fewer but more visually similar results.
min_views	integer	null	Minimum video view count filter
max_views	integer	null	Maximum video view count filter

YouTube Scraper

TOOL scrape_youtube

Scrape video data from a YouTube channel or single video. Returns metadata, transcripts, and top comments (sorted by likes). Async — submits a job, polls until complete, returns final results.

Example prompt

"Scrape the last 10 videos from @MrBeast and include transcripts and comments"

Parameter	Type	Default	Description
url	string	required	YouTube channel URL or video URL
video_type	string	both	Type of videos: `shorts`, `videos`, or `both`
sort	string	recent	Sort order: `recent` or `popular`
max_videos	integer	20	Maximum videos to scrape (1-100)
include_transcripts	boolean	false	Include full video transcripts
include_comments	boolean	false	Include top comments for each video (sorted by likes)

Context limits: To keep responses within Claude's context window, transcripts are trimmed to 5,000 characters per video and comments are limited to 20 per video (top by likes, 300 chars each).

TOOL read_transcript

Fetch full transcript text for YouTube videos. Pass one or more transcript_url values from scrape_youtube results (comma-separated for batch). All URLs are fetched in parallel. Returns complete transcripts with no truncation.

Example prompt

"Read the transcript for the first video from the scrape results"

Parameter	Type	Default	Description
transcript_url	string	required	One or more `transcript_url` values from `scrape_youtube` results. Pass a single URL or multiple comma-separated URLs to fetch all in parallel.

Workspace

Organize channels into folders, save and manage your research. 30 channels per folder hard cap on all plans.

TOOL list_folders

List the user's saved folders with channel counts. Returns folder name, ID, channel count, and creation date for each folder. No parameters required.

Example prompt

"Show me my saved folders"

TOOL create_folder

Create a new folder for organizing saved channels. Returns 409 if a folder with this name already exists. Folder limits: Starter 15, Pro 50, Ultimate unlimited.

Example prompt

"Create a folder called 'Cooking Research'"

Parameter	Type	Default	Description
name	string	required	Folder name (1–50 chars, must be unique per user)

TOOL rename_folder

Rename an existing folder. Pass the current folder name (or ID) and the new name. Returns 409 if the new name collides with another existing folder.

Parameter	Type	Default	Description
folder	string \| integer	required	Current folder name OR folder ID
new_name	string	required	New folder name (1–50 chars, must be unique)

TOOL delete_folder

Delete a folder AND unsave every channel in it. Destructive — the first call (confirm=false) returns a preview with the channel count so the user can confirm. There is no Uncategorized fallback.

Parameter	Type	Default	Description
folder	string \| integer	required	Folder name OR folder ID to delete
confirm	boolean	false	Set to `true` to confirm deletion. First call returns the channel count so you can warn the user before they confirm.

TOOL get_folder

Get all channels in a folder with live 24h growth metrics. Returns each channel's current subscriber count, view count, and the latest 24h delta (views_24h, subs_24h).

Example prompt

"What's new with my Cooking Research folder?"

Parameter	Type	Default	Description
folder	string \| integer	required	Folder name OR folder ID

TOOL save_channels

Save one or more channels to a folder. Channel IDs must be raw YouTube channel IDs (start with UC, 24 chars). For @handles or URLs, call resolve_handle / resolve_url first. 30 channels per folder hard cap.

Example prompt

"Save the top 3 channels from my last search to 'Cooking Research'"

Parameter	Type	Default	Description
channel_ids	list[string]	required	List of YouTube channel IDs (`UCxxxxxxxxxxxxxxxxxxxxxx`). Must be raw IDs — call `resolve_handle` or `resolve_url` first to convert @handles or URLs.
folder	string \| integer	required	Folder name OR folder ID. There is no default folder — must be specified.

TOOL unsave_channel

Remove a channel from the user's saved set. The channel disappears from whichever folder it was in.

Parameter	Type	Default	Description
channel_id	string	required	YouTube channel ID (`UCxxxxxxxxxxxxxxxxxxxxxx`) to remove from saved channels

TOOL move_channel

Move an already-saved channel from its current folder to a different one. Returns 404 if the channel isn't currently saved. Returns 409 if the target folder is at the 30-channel cap.

Parameter	Type	Default	Description
channel_id	string	required	YouTube channel ID (`UCxxxxxxxxxxxxxxxxxxxxxx`) to move
to_folder	string \| integer	required	Destination folder name OR folder ID

Resolvers

Convert @handles and URLs to stable channel IDs for use with workspace tools. These are narrow-use tools — search tools auto-resolve handles and URLs internally.

TOOL resolve_handle

Resolve a YouTube @handle to a stable channel ID. Use only when you need a raw channel ID for save_channels. Search tools already auto-resolve handles — do NOT call this before searching.

Example prompt

"Save @cheftok to my Cooking Research folder"

Parameter	Type	Default	Description
handle	string	required	A YouTube @handle (e.g. `@cheftok` or `cheftok`). The leading `@` is optional.

TOOL resolve_url

Resolve a YouTube channel URL or video URL to a stable channel ID. For video URLs, the owner channel is returned. Use only when you need a raw channel ID for save_channels.

Parameter	Type	Default	Description
url	string	required	A YouTube channel URL (`youtube.com/@handle`, `youtube.com/channel/UCxxx`) or video URL (`watch`, `shorts`, `youtu.be`). For video URLs the owner channel is returned.

Alerts

Set up growth alerts on channels, folders, and saved searches. Alerts fire once a night and show once the next morning. Plan limits: Starter 3, Professional 25, Ultimate unlimited.

TOOL list_alerts

List all the user's active alerts (paused and unpaused). No parameters required.

Example prompt

"What alerts do I have?"

TOOL create_alert

Create a growth alert. Fires once a night when the threshold is crossed. Three target types: channel (single channel), folder (any channel in a folder), search (new channels matching a saved search).

Example prompt

"Alert me when any channel in my Cooking Research folder gains 5000+ subs in 24 hours"

Parameter	Type	Default	Description
target_type	string	required	What the alert watches: `channel` (single channel), `folder` (any channel in a folder), or `search` (new channels matching a saved search).
target_value	object	required	Shape depends on target_type: `{"channel_id": "UCxxx..."}` for channel, `{"folder_id": 47}` for folder, `{"query": {"q": "cooking", "max_subs": 100000, "content_type": "shorts"}}` for search.
metric	string	required	What to measure: `subs_24h` (subscriber gain in last 24h), `views_24h` (view gain), `subscriber_count`, `avg_views`, `total_videos`, `view_count`, `avg_duration`, `video_outlier` (new video's views vs channel avg), or `new_channels` (count of new search matches — search target only).
threshold	number	required	Fire when the metric value is >= this number. E.g. `5000` with metric `subs_24h` means "fire when channel gains 5000+ subs in 24h". For `video_outlier`, this is a float multiplier — e.g. `2.5` fires when a new video gets 2.5x or more views than the channel's average per video.

TOOL pause_alert

Pause an alert without deleting it. Resume later with unpause_alert.

Parameter	Type	Default	Description
alert_id	integer	required	Alert ID from `list_alerts`

TOOL unpause_alert

Resume a previously paused alert.

Parameter	Type	Default	Description
alert_id	integer	required	Alert ID from `list_alerts`

TOOL delete_alert

Permanently delete an alert. Also deletes all its triggered_alerts history.

Parameter	Type	Default	Description
alert_id	integer	required	Alert ID from `list_alerts`

TOOL get_outlier_alert_status

Get diagnostic status for the user's video_outlier alerts. Returns what the nightly evaluator looked at, what it skipped and why, and the top 10 near-miss channels. Use this to answer "what did my alert find yesterday" or "why hasn't it fired yet". Unlike get_triggered_alerts, this shows every run — including ones where nothing met the threshold. Data is from the last evaluator run (a checked_at_human field like "3 hours ago" tells you how fresh).

Example prompt

"What's the status of my outlier alerts? How close are any of them to firing?"

No parameters. Returns one entry per video_outlier alert with state (checked / never_checked / paused), summary (channels total / with uploads / skipped breakdown / top_outlier_score), and near_misses (array of up to 10 channels whose top video scored at least 10% of the threshold, each with per-condition pass/fail).

TOOL get_triggered_alerts

Get the user's alert inbox — the morning-briefing tool. By default returns alerts that have fired since the user last checked and marks them as seen. Set include_acknowledged=true for read-only history mode.

Example prompt

"Any alerts this morning?"

Parameter	Type	Default	Description
since	string	null	Optional duration filter: `24h`, `7d`, `30d`. Limits results to alerts that fired within this window.
include_acknowledged	boolean	false	Default false (inbox mode). Set `true` for read-only history mode that includes already-seen alerts and does NOT mark new ones as seen.

Text-to-Speech

Browse voices, generate audio, and check job status. Supports both ElevenLabs and Stealth TTS providers.

TOOL list_voices

Browse and search available TTS voices. Returns voice IDs, names, previews, and metadata. Set stealth=true for Stealth provider voices.

Example prompt

"Show me young male American English voices"

Parameter	Type	Default	Description
search	string	null	Search by voice name or labels
gender	string	null	Filter: `male`, `female`, or `neutral`
age	string	null	Filter: `young`, `middle_aged`, or `old`
language	string	null	Language code (e.g. `en`, `es`, `fr`)
accent	string	null	Filter by accent (e.g. `american`, `british`)
sort	string	trending	Sort: `trending`, `created_date`, `usage_character_count_1y`
page_size	integer	30	Results per page (max 100)
page	integer	0	Page number (0-indexed)
stealth	boolean	false	Use Stealth voices endpoint instead of ElevenLabs

TOOL generate_tts

Generate text-to-speech audio. Submits a job, polls until complete, returns the permanent hosted audio URL.

Example prompt

"Generate a voiceover using the voice 'Adam' saying: Welcome to today's video about productivity tips"

Parameter	Type	Default	Description
script	string	required	Text to convert to speech (max 200,000 characters)
voice_id	string	required	Voice ID from `list_voices`, or voice name for Stealth provider
provider	string	elevenlabs	TTS provider: `elevenlabs` or `stealth`
model_id	string	null	ElevenLabs model (e.g. `eleven_multilingual_v2`, `eleven_flash_v2_5`)
stability	float	null	Voice consistency 0.0-1.0 (ElevenLabs only)
similarity_boost	float	null	Voice match accuracy 0.0-1.0 (ElevenLabs only)
style	float	null	Style exaggeration 0.0-1.0 (ElevenLabs only)
speed	float	null	Playback speed 0.7-1.2 (ElevenLabs only)
temperature	float	null	Expressiveness — higher is more expressive (Stealth only)
speaking_rate	float	null	Speaking speed multiplier (Stealth only)
voice_name	string	null	Human-readable voice label for your reference
custom_title	string	null	Custom filename for output MP3 (without extension)
generate_srt	boolean	false	Generate SRT subtitle file (ElevenLabs only)

TOOL get_tts_job_status

Check the status of a TTS generation job. Use this to retrieve the audio_url for a previously submitted job.

Parameter	Type	Default	Description
job_id	string	required	Job ID returned from `generate_tts`

TOOL list_tts_jobs

List your recent TTS generation jobs, sorted by creation time (newest first). No parameters required.

Example prompt

"Show me my recent TTS generations"

TOOL clone_voice

Clone a voice using the Stealth voice engine. Upload an audio sample and get a reusable voice ID. Requires an active subscription.

Example prompt

"Clone this voice sample as 'My Narrator' using the audio at https://example.com/sample.mp3"

Parameter	Type	Default	Description
display_name	string	required	Display name for the cloned voice
audio_url	string	required	URL to the audio sample (MP3, WAV, M4A, OGG, WEBM; max 15MB)
lang_code	string	EN_US	Language code (e.g. EN_US, ES_MX, FR_FR, DE_DE, JA_JP)
description	string	null	Description of the voice

TOOL delete_voice

Delete a cloned Stealth voice by ID.

Parameter	Type	Default	Description
voice_id	string	required	ID of the cloned voice to delete

Media Generation

TOOL generate_image

Generate an AI image from a text prompt. Requires Professional or Ultimate plan. Costs 2–3 studio credits depending on model.

Example prompt

"Generate a thumbnail image of a mysterious dark forest with glowing eyes, 16:9 aspect ratio"

Parameter	Type	Default	Description
prompt	string	required	Description of the image to generate
model	string	nano-banana-2	Model: `nano-banana-2` (2 credits, default), `nano-banana-pro` (3, supports up to 8 reference images), `seedream-4.5-edit` (2, requires reference_image_url), `seedream-5.0-lite` (2, optional reference)
aspect_ratio	string	16:9	Aspect ratio (e.g. 16:9, 9:16, 1:1)
reference_image_url	string	null	Optional reference image URL

TOOL generate_video

Generate an AI video from a text prompt. Requires Professional or Ultimate plan. Costs 3–30 studio credits depending on model and duration.

Example prompt

"Generate a 4-second vertical video of a cat walking through a neon-lit city at night using sora-2"

Parameter	Type	Default	Description
prompt	string	required	Description of the video to generate
model	string	sora-2	Model: `sora-2`, `kling-2.6`, `veo3-fast`, `grok-image-to-video`
seconds	string	4	Duration for sora-2 (4, 8, or 12 seconds)
size	string	720x1280	Resolution (e.g. 720x1280, 1280x720)
duration	string	5	Duration for kling model (5 or 10 seconds)
sound	boolean	false	Include audio (kling only)
aspect_ratio	string	9:16	Aspect ratio (e.g. 9:16, 16:9)
input_reference_url	string	null	Reference image URL

TOOL remove_captions

Remove captions or watermarks from a video. Costs 12 credits per minute (0.2 per second, rounded up). Requires Professional or Ultimate plan.

Parameter	Type	Default	Description
video_url	string	required	URL of the video to remove captions from

TOOL remove_sora_watermark

Remove the Sora watermark from a video. Costs 2 studio credits. Requires Professional or Ultimate plan. URL must be from sora.chatgpt.com.

Parameter	Type	Default	Description
video_url	string	required	Sora video URL (must be from sora.chatgpt.com)

Utility

TOOL health_check

Check API health and view current job counts. Useful for verifying your connection is working.

Example prompt

"Check if the Algrow API is up"

Example Prompts

Once the MCP server is connected, just ask Claude in plain English. Here are some examples to get started:

Channel Discovery

"Search for 'roblox' English Shorts channels under 10k subs that are less than 90 days old and growing fast"

Niche Research

"Search for 'history documentary' longform channels with under 50k subs that are monetized"

Viral Video Analysis

"Find the top viral Shorts about AI tools uploaded in the last 3 days"

Competitor Research

"Scrape the last 20 videos from @AlexHormozi and include transcripts so I can analyze his content strategy"

TTS Generation

"List trending male voices, then generate a voiceover for this script: [paste script]"

Combined Workflow

"Find 5 viral Shorts about fitness, scrape the top performing channel, and summarize their content strategy"

Limits

Limit	Value	Applies to
Requests per minute	30	All tools
Max page number	20	Search tools
Max results per page	50	Search tools
Max results per query	1,000	Search tools (20 pages × 50 results)
Max concurrent jobs	5	TTS, scraper, media generation
Max videos per scrape	100	`scrape_youtube`
Max script length	200,000 chars	`generate_tts`

Search query required: All search tools (search_shorts_channels, search_longform_channels, search_viral_videos) require a search query. Browsing without a query is not supported.

Troubleshooting

Server not appearing in Claude Code

Run /mcp in Claude Code to see connected servers
Check your ~/.claude.json syntax with a JSON linter
Restart Claude Code completely

Server not appearing in Claude Desktop

Restart Claude Desktop completely (not just close the window)
Verify config file path is correct for your OS
Check JSON syntax — a trailing comma will break it
Look for the MCP indicator (hammer icon) in the chat input area

API key errors

Verify your API key at algrow.online/settings
Make sure the key is in the Authorization header, not args or env
Check your subscription is active (Professional or Ultimate plan required)

Still stuck? Contact support at support@algrow.online or check the REST API docs to verify your API key works with direct HTTP requests.

Algrow MCP Server

Setup

What is MCP?

Get your API key

Pick your platform

Start asking

Channel Search

Channel Data

Terminated Channels

Viral Videos

Thumbnail Search

YouTube Scraper

Workspace

Resolvers

Alerts

Text-to-Speech

Media Generation

Utility

Example Prompts

Limits

Troubleshooting

Server not appearing in Claude Code

Server not appearing in Claude Desktop

API key errors

Buy More Credits