TollNode

Threads data API and MCP server for AI agents

TollNode gives Claude, Cursor or any AI agent public Threads data (search posts by keyword or read an account's latest posts) over API and MCP, from $0.062 per call, no subscription.

Ask in plain words, like 'what is National Geographic posting on Threads', and get a clean table back in seconds.

No subscription · Sign-up optional · From $0.062 per call · Charged only when it works · No Threads account needed

Claude Code

Get National Geographic's latest Threads posts with engagement

TollNode · Threads · posts$0.062 · 10 posts · 14 s

PostLikesReplies
Yes, we'd love for you to show us the...829394
There’s more than slime hiding in this...561
Whatever caught this cub’s eye has our...2143
+7 more

Real result.

Works in Claude Code, Cursor, Codex, VS Code and any MCP agent.

What your agent can pull from Threads

Every result is structured JSON your agent can sort, filter, summarize or turn into a spreadsheet.

What people ask their AI to do with it

Use it as a Threads data MCP server in Claude, Cursor or Codex

Connect once. Then just ask.

Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.

terminal
npx agentcash add https://tollnode.com

Copy for your AI agent

Paste this into your agent so it knows what this node does and how to call it.

prompt
You can use TollNode's Threads data node. Call POST https://tollnode.com/api/v1/nodes/threads with an "action" (search, posts) and its fields: sort (optional), query (optional), handle (optional). Each action has its own price and is charged only when it returns a result. Over MCP, call the "threads" tool; use list_models to see prices. Return results as tables when I ask for lists.

2 actions, one node

Send action plus the fields that action needs, to the same address. Each action has its own price, charged only when it returns a result. Leave out action and you get search.

  • search$0.062

    Search public posts for a keyword or hashtag. 10 posts: text, author handle, date, likes, replies, reposts, views where shown, and post link..

    needs: query · optional: sort

  • posts$0.062

    An account's latest 10 posts. 10 posts: text, date, likes, replies, reposts, quotes, views, media links, hashtags and post link..

    needs: handle

request body: search
{"action":"search","query":"AI agents"}
request body: posts
{"action":"posts","handle":"natgeo"}

POST either body to https://tollnode.com/api/v1/nodes/threads. From an AI assistant you don't write this yourself: ask in plain words and it picks the action.

Charged only when a call returns a result. Failed or empty calls cost $0.

Threads data without a scraper

FAQ

Is this the official Threads API?
No. Meta's Threads API needs an app and review. TollNode returns public Threads data through its own API and MCP server, priced per action.
Can I use it as a Threads data MCP server in Claude?
Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the "threads" tool appears with its fields and price.
What are the two actions?
search finds public posts for a keyword or hashtag (sort top or recent). posts returns an account's latest posts when you send the handle without @.
Are view counts always there?
No. Threads hides views on some posts, and the field says so when it is not public yet.
Can it read private accounts?
No. Public accounts and posts only, no follower lists or messages.
What if nothing comes back?
You're not charged. TollNode only collects payment when a usable result is returned, and your agent can try a different input.
How do I pay for Threads data?
Your agent sends the request, gets an HTTP 402 with the exact price (from $0.062 per call), signs a USDC payment on Base and retries. Or use an account balance with an API key. Either way you are charged only when a result comes back.
What does the Threads data response look like?
Structured JSON, with the fields listed in the cards above. Your agent can sort it, filter it, summarize it or turn it into a table or spreadsheet.

Ready in a minute

Connect your AI
For developers: endpoint, inputs and an example response

POST https://tollnode.com/api/v1/nodes/threads

Input

FieldTypeNotes
sortenumtop (most relevant) or recent (newest first). Default top (for: search) (top, recent)
querystringKeyword or hashtag to search, e.g. AI agents (for: search)
action*enumWhat to do; sets the price. search (needs query), posts (needs handle). Default search (search, posts)
handlestringThreads username without @, e.g. natgeo (for: posts)

Example response

{
  "results": [
    {
      "is_gif": false,
      "is_reply": false,
      "post_url": "https://www.threads.com/@julienrenaux_/post/DfxaadKj0Xp",
      "has_audio": null,
      "has_media": true,
      "is_edited": false,
      "is_pinned": false,
      "is_repost": false,
      "post_code": "DfxaadKj0Xp",
      "created_at": "2026-11-15T18:21:31+00:00",
      "like_count": 5,
      "media_type": "photo",
      "repost_url": "",
      "view_count": null,
      "media_width": 1440,
      "music_title": "",
      "quote_count": 0,
      "record_type": "post",
      "reply_count": 6,
      "repost_code": "",
      "reposted_at": "",
      "share_count": null,
      "media_height": 1440,
      "music_artist": "",
      "repost_count": 0,
      "is_quote_post": false,
      "music_song_id": "",
      "reply_control": "everyone",
      "sticker_count": 0,
      "poll_is_closed": null,
      "is_ai_generated": false,
      "is_sticker_post": false,
      "quoted_post_url": "",
      "replied_to_text": "",
      "poll_total_votes": null,
      "reply_to_username": "",
      "reposted_post_url": "",
      "view_count_status": "not_public_yet",
      "created_at_display": "2026-11-15 18:21 UTC",
      "is_paid_partnership": false,
      "replied_to_post_url": "",
      "reposted_by_user_id": "",
      "replied_to_available": null,
      "replied_to_post_code": "",
      "reposted_by_username": "",
      "accessibility_caption": "",
      "replied_to_created_at": "",
      "replied_to_like_count": null,
      "replied_to_author_user_id": "",
      "replied_to_author_username": ""
    }
  ]
}

Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.