mcpField
I
instagram-research

instagram-research

github.com/crawlora-orgOther139 installsUpdated 2d ago
Repository

About instagram-research

A skill for retrieving public Instagram profile, Reels, and post data as normalized JSON through the Crawlora API. It is intended for social research such as influencer checks and competitor audits, with lookups limited to public content.

Key features

  1. 01Look up public profiles
  2. 02Retrieve paginated Reels feeds
  3. 03Get details for a single post
  4. 04Use numeric IDs for Reels and post lookups

Use cases

  1. 01Check an influencer's follower count and content mix
  2. 02Review a competitor's profile and recent Reels
  3. 03Inspect engagement details for a known post

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/crawlora-org/crawlora-skills --skill instagram-research

After installing, type/instagram-researchin Claude Code to confirm it loaded.

Bundled filesreference/endpoints.mdscripts/crawlora.sh

Details

From the project README

Instagram research

Look up public Instagram profiles, posts, and Reels — all as normalized JSON from the Crawlora API, no app scraping or unofficial client libraries.

When to use this skill

  • "What's 's Instagram profile / follower count?"
  • "Pull the details for this Instagram post."
  • "Get 's recent Reels."
  • Competitor social audits, influencer vetting, or brand-mention monitoring scoped to Instagram.

Setup (one-time)

  • Get a free Crawlora API key (2,000 credits/mo, no card) at https://crawlora.net.
  • Set CRAWLORA_API_KEY in the environment before running the helper.
  • The helper reads CRAWLORA_API_KEY from the environment and sends requests to https://api.crawlora.net/api/v1. Missing/invalid key → 401.

How it works

  1. Profile — /instagram/profile/{username} returns public profile details for a given Instagram username.
  2. Reels — /instagram/reels/{id} returns a feed of Reels for an Instagram user ID, paginated via the optional max_id cursor.
  3. Post detail — /instagram/post/{id}/{post_id} returns the media details of a specific post, keyed by Instagram user ID and post ID.

Full endpoint list, methods, and params: reference/endpoints.md.

Calling the API

# Profile:
scripts/crawlora.sh /instagram/profile/nasa | jq '.'

# Reels feed (paginate with max_id from the previous response):
scripts/crawlora.sh /instagram/reels/528817151 | jq '.'
scripts/crawlora.sh /instagram/reels/528817151 max_id=<cursor> | jq '.'

# Post detail (requires both the user ID and the post ID):
scripts/crawlora.sh /instagram/post/528817151/3123456789012345678 | jq '.'

Use scripts/crawlora.sh for all requests; it keeps the API key out of command-line arguments.

Endpoint reference

See reference/endpoints.md for every Instagram endpoint this skill uses.

Examples

  • Influencer vetting: profile + Reels feed to check follower count, posting cadence, and content mix before a partnership.
  • Competitor social audit: pull a competitor's profile stats and recent Reels to gauge follower growth and content strategy over time.
  • Post-level engagement check: given a known post URL, extract the user ID and post ID, then call /instagram/post/{id}/{post_id} for that post's media details.

Notes & limits

  • Credits / pay-on-success: billed only on 2xx; free tier 2,000 credits/mo. Key at https://crawlora.net.
  • Public data only — public profiles/posts; no login, no private content. Respect Instagram's terms.
  • Security: key lives in CRAWLORA_API_KEY only — never hardcode, query-param, or commit it.
  • Numeric user ID, not username, for Reels and post lookups — /instagram/reels/{id} and /instagram/post/{id}/{post_id} both key off Instagram's internal numeric user ID, not the @username; get it from the /instagram/profile/{username} response first if you only have a handle.
  • Narrow public surface — this skill covers profile lookup, Reels feed, and single-post detail only; there is no keyword/hashtag search or trending endpoint for Instagram.
  • Reels pagination is cursor-based via max_id — follow the cursor returned in the response to walk beyond the first page.

Comments

Markdown supported