MCP quickstart

Name: ShortsIntel
Availability: InStock
Rating: 4.8 (1024 reviews)
Author: ShortsIntel

ShortsIntel runs a remote MCP server with 13 tools for short-form video research. Connect it once and your assistant can search, enrich, score and track TikTok, Instagram Reels and YouTube Shorts — and quote you a price before it spends anything.

Endpoint: https://www.shortsintel.com/api/mcp

Transport: streamable HTTP

Auth: an API key as a bearer token, or OAuth 2.1 where the client supports it

Get a key

Create one in the console. It is shown once, has no expiry, and can be revoked at any time. New accounts start with a $5 credit that expires after 90 days. Claude.ai connects over OAuth instead and needs no key at all.

Connect your client

Claude.ai (web and desktop)

Settings → Connectors → Add custom connector. Paste the endpoint and sign in when prompted — Claude.ai negotiates OAuth on its own, so there is no key to paste and no config file to edit. At consent you pick which organization’s balance the connection spends from.

https://www.shortsintel.com/api/mcp

Claude Code

One command, from any directory. Drop --scope user to add it to the current project only.

claude mcp add --transport http shortsintel https://www.shortsintel.com/api/mcp \
  --scope user \
  --header "Authorization: Bearer sk_live_YOUR_KEY"

Then run /mcp inside Claude Code to confirm the 13 tools are listed.

Cursor

Settings → MCP → Add new global MCP server, or create .cursor/mcp.json in the project.

{
  "mcpServers": {
    "shortsintel": {
      "type": "http",
      "url": "https://www.shortsintel.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_YOUR_KEY"
      }
    }
  }
}

VS Code (GitHub Copilot agent mode)

Add .vscode/mcp.json to the workspace. The inputs block makes VS Code prompt for the key and store it in the OS keychain rather than writing it into a file you might commit.

{
  "inputs": [
    {
      "type": "promptString",
      "id": "shortsintel-key",
      "description": "ShortsIntel API key",
      "password": true
    }
  ],
  "servers": {
    "shortsintel": {
      "type": "http",
      "url": "https://www.shortsintel.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${input:shortsintel-key}"
      }
    }
  }
}

The tools

Every paid tool accepts estimate, which returns the price without running anything or charging you, and an optional idempotency_key: retrying with the same key returns the original run and is not charged again. Tools wait up to 60 seconds inline and then hand back a run id to poll with get_run; re-reading a run is always free. Cached results cost 25% of fresh, and failed work is never charged.

Paid

Tool	What it does	Price
`research`	Research a niche	$0.50 for up to 50 enriched videos, then $0.01 each, at most $2.00
`search_videos`	Search videos	$0.01 per page; +$0.02 per enriched video with intelligence=true (top 20)
`get_video`	Get a video	$0.005 plain ($0.00125 cached); with include=intelligence $0.02 ($0.005 cached) instead; transcript only $0.005 instead
`score_video`	Score a video	$0.05
`get_creator`	Get a creator	$0.02
`get_hashtag_or_sound`	Get a hashtag or sound	$0.02
`search_ads`	Search ad libraries	$0.02 per page
`track`	Track a target	$0.05 per cycle, including the first one run on create; +$0.02 per new video with intelligence

Free

list_trackers — List trackers
get_changes — Get change reports
get_run — Get a run
get_usage — Get usage
get_balance — Get balance

Also worth knowing

Limits are 60 requests per minute and 10 concurrent running operations.
Before any work starts, the Balance is checked against the operation's quoted price (for Research and enriched searches, the worst-case quote). If it cannot cover that, the call is a `402 insufficient_balance` and no Run is created or charged. A multi-item Run (Research, enriched search) settles per item when it finishes. If the Balance no longer covers every completed item, the completed items are charged in order up to the Balance, the rest fail with `insufficient_balance`, and the Run ends `partial`. A Run that cannot afford any of its work ends `failed` and is not charged.
Instagram coverage is best-effort and is reported as coverage: "partial" rather than silently returning less.
The same operations are available over REST — see the API reference, or /llms-full.txt if you would rather hand your agent one file.
Discovery document: /.well-known/mcp/server-card.json.

Something not connecting? Email support@shortsintel.com.