New: the Scrapier MCP server. Every scraper in Claude Code with one command. See how →
GET/api/v2/twitter-post/

Twitter Post Scraper MCP Server

Give Claude, Cursor and ChatGPT a tool for any public X (Twitter) page of posts. One command connects it; every call returns typed JSON. 1 credit per page of posts.

Free API key · 1 credit per page of posts · failed calls free

Last updated
Live agent run
Copy for your AI agent
Install

Connect in one command

Quick answerScrapier's MCP server gives Claude, Cursor and any MCP client tools for public X (Twitter) pages of posts, returned as JSON. One command connects it. Each call costs 1 credit.
terminal
claude mcp add -t http scrapier \
  https://mcp.scrapier.io/mcp \
  --header "X-API-Key: YOUR_API_KEY"
Then ask: "Get the X (Twitter) page of posts for elonmusk"
Connect

Custom connector

Connect any client that supports remote MCP with one URL and your API key.

Custom connector

Any MCP client

Paste one URL into any client that supports remote MCP and send your Scrapier API key in an X-API-Key header.

https://mcp.scrapier.io/mcp
Where to paste it
  • ClaudeSettings → Connectors → Add
  • ChatGPTSettings → Apps → Developer mode → Create
  • CursorSettings → MCP → Add new server
Step-by-step setup ↓
Setup

Setup in Claude, Cursor, Windsurf and ChatGPT

Pick your client. Three steps, under a minute.

  1. Get a free API key from your Scrapier dashboard.
  2. Run the command below in your terminal.
  3. Restart Claude Code and run /mcp to see the tools.
terminal
claude mcp add -t http scrapier https://mcp.scrapier.io/mcp --header "X-API-Key: YOUR_API_KEY"
claude · ~/project
› /mcp
Manage MCP servers
● scrapier · connected · 6 tools
└ search_endpoints
└ run_scrape
└ …4 more
›

Verify the connection

Ask "List your X (Twitter) tools". The agent should find run_scrape and search_endpoints.

Tools

X (Twitter) MCP Tools

Use search_endpoints to discover, run_scrape to call.

ToolReturnsInputsKey fieldsCredits
run_scrapeRun the page of posts scraperendpoint="twitter-post", usernames="..."biography, bookmarks, date_posted, description, external_url1

Output fields

run_scrape · 200 OK
{
  "success": true,
  "data": {
    "usernames": "https://x.com/elonmusk/status/1585341984679469056",
    "page": 1,
    "page_size": 1,
    "tweets": [
      {
        "biography": "",
        "bookmarks": 16000,
        "date_posted": "2022-10-26T18:45:58.000Z",
        "description": "Entering Twitter HQ – let that sink in! https://t.co/D68z4K2wq7",
        "external_url": null,
        "followers": 241733278,
        "following": 1300,
        "hashtags": null,
        "id": "1585341984679469056",
        "input": {
          "url": "https://x.com/elonmusk/status/1585341984679469056/"
        },
        "is_verified": true,
        "likes": 1221559,
        "name": "Elon Musk",
        "photos": null,
        "posts_count": 98000,
        "profile_image_link": "https://pbs.twimg.com/profile_images/example_normal.jpg",
        "quoted_post": {
          "date_posted": null,
          "description": null,
          "post_id": null,
          "profile_id": null,
          "profile_name": null,
          "url": null,
          "videos": null
        },
        "quotes": 70000,
        "replies": 160000,
        "reposts": 200000,
        "tagged_users": null,
        "url": "https://x.com/elonmusk/status/1585341984679469056",
        "user_posted": "elonmusk",
        "videos": [
          "https://video.twimg.com/ext_tw_video/1585341912877146112/pu/vid/1920x1080/example.mp4?tag=14"
        ],
        "views": null,
        "input_username": "https://x.com/elonmusk/status/1585341984679469056"
      }
    ],
    "next_cursor": null
  }
}
Examples

Example Prompts and Tool Calls

The prompt, the tool call, the JSON and the answer.

Get page of posts data

Get the page of posts data for elonmusk.
⚙ run_scrape(endpoint="twitter-post", usernames="elonmusk")
run_scrape(endpoint="twitter-post", usernames="elonmusk")
{
  "biography": "",
  "bookmarks": 16000,
  "date_posted": "2022-10-26T18:45:58.000Z",
  "description": "Entering Twitter HQ – let that sink in! https://t.co/D68z4K2wq7"
}
Here are the page of posts details from the Scrapier API.
Workflows

Agent Workflows

X (Twitter) data pipeline

  1. input list
  2. run_scrape
  3. filter results
  4. export

Feed a list, pull each page of posts, filter by criteria, export the result.

Compare

X (Twitter) Scraper MCP vs the Official X (Twitter) MCP

Scrapier X (Twitter) MCPThis pageOfficial X (Twitter) APIApify actor over MCP
Data returnedAny public page of posts, typed JSONYour own accounts and insightsVaries by actor
Auth neededOne Scrapier keyX (Twitter) app + business accountApify token
Cost model1 credit per callFree once approvedCompute units per run
Rate limits3 parallel per keyPer-user hourly quotaPer actor
Best forResearch, enrichment, monitoringOwn-account analyticsCustom one-off crawls

Limits

  • Public data only — private pages of posts return identity fields only
  • Counts are live at call time; no history unless you store it
Billing

Credits, Rate Limits and Security

Credits per call1
Parallel requests3 per key
AuthOne Scrapier key, no X (Twitter) login
  • Your key stays in your client config, never in prompts
  • No X (Twitter) account or cookies are used
  • Failed calls cost 0 credits
  • Rotate or revoke keys any time from the dashboard

See full pricing →

Troubleshooting

Troubleshooting

Tools not showing

Restart the client after editing its config. In Claude Code run /mcp; in Cursor check the server toggle is on.

401 invalid key

The key is missing or mistyped. Copy it again from the dashboard.

429 rate limit

You exceeded your plan's parallel requests. The agent should wait for Retry-After.

Timeout on large requests

Batch in smaller groups, or raise the client timeout to 210 seconds.

FAQ

Frequently Asked Questions

Is there a X (Twitter) scraper MCP server?

Yes. Scrapier's MCP server exposes X (Twitter) page of posts tools to Claude, Cursor, Windsurf and ChatGPT. One command connects it and every call returns typed JSON.

How do I scrape X (Twitter) pages of posts with Claude?

Run <code>claude mcp add -t http scrapier https://mcp.scrapier.io/mcp</code> with your API key, then ask Claude for any public page of posts. It calls <code>run_scrape</code> and reads the JSON directly.

Does it need a X (Twitter) login?

No. The server reads public data only and uses no X (Twitter) account or cookies.

How much does a X (Twitter) MCP call cost?

1 credit per call — about $1.58 per 1,000 pages of posts on the Pro plan. Failed calls are free.

Can ChatGPT use the X (Twitter) scraper?

Yes. Add Scrapier as a custom connector in ChatGPT's developer mode and the same tools appear in chat.

Give your agent X (Twitter) data

1 tool · JSON · one key