mcpField
T
threads-research

threads-research

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

About threads-research

A research skill for retrieving public Threads profiles, posts, replies, and keyword search results as normalized JSON through Crawlora. It is intended for public conversation research, including profile reviews and brand or topic monitoring.

Key features

  1. 01Retrieve public profile details
  2. 02Fetch paginated profile posts
  3. 03Read posts and public replies
  4. 04Search public posts by keyword

Use cases

  1. 01Review a profile and recent posts
  2. 02Inspect a post and its replies
  3. 03Monitor public discussion of a brand
  4. 04Search for conversation about a topic

Install

Copy the command and run it in a terminal.

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

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

Bundled filesreference/endpoints.mdscripts/crawlora.sh

Details

From the project README

Threads research

Look up public Threads profiles, posts, and replies, and run keyword search — all as normalized JSON from the Crawlora API, no app scraping or unofficial client libraries.

When to use this skill

  • "What's 's profile / follower count on Threads?"
  • "Pull this Threads post's text and replies."
  • "What has posted recently on Threads?"
  • "Search Threads for posts about ."
  • Competitor social-listening or brand-mention monitoring on Threads.

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 — /threads/profile/{username} for public profile metadata (bio, counts).
  2. Profile posts — /threads/profile/{username}/posts for a profile's public posts, paginated via an opaque cursor.
  3. One post — /threads/post/{username}/{code} for a single post's text, author, canonical URL, and preview image.
  4. Post replies — /threads/post/{username}/{code}/replies for the public replies to that post.
  5. Search — /threads/search for the public first page of Threads search results for a query.

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

Calling the API

# Profile + posts:
scripts/crawlora.sh /threads/profile/zuck | jq '.'
scripts/crawlora.sh /threads/profile/zuck/posts | jq '.'

# Post + replies:
scripts/crawlora.sh /threads/post/zuck/C1abc2DEfGh | jq '.'
scripts/crawlora.sh /threads/post/zuck/C1abc2DEfGh/replies | jq '.'

# Search:
scripts/crawlora.sh /threads/search q="web scraping" | 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 Threads endpoint this skill uses.

Examples

  • Profile snapshot: /threads/profile/{username} for bio and follower counts, then /threads/profile/{username}/posts to see recent activity.
  • Post deep-dive: /threads/post/{username}/{code} for a specific post's text, then /threads/post/{username}/{code}/replies to read what people are saying about it.
  • Keyword sweep: /threads/search for a brand or topic name to gauge how much public conversation is happening on Threads right now.

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 Threads' terms.
  • Security: key lives in CRAWLORA_API_KEY only — never hardcode, query-param, or commit it.
  • Search has no continuation cursor — /threads/search returns only the logged-out first page of results; there's no way to page deeper.
  • Reply pagination is opaque and sometimes absent — /threads/post/{username}/{code}/replies will flag when Threads reports more replies exist but can withhold a usable cursor to fetch them.
  • Profile posts paginate via cursor — pass the cursor from the previous /threads/profile/{username}/posts response to walk beyond the first page.

Comments

Markdown supported