x-mcp-server

An MCP server that scrapes public content from X (formerly Twitter) using a stealth Patchright browser, exposed over FastMCP. Designed to run with uvx, so any MCP client can launch it with zero local setup.

Inspired by stickerdaniel/linkedin-mcp-server.

Disclaimer: This is an independent, community project. It is not affiliated with, authorized by, endorsed by, or sponsored by X Corp. "X" and "Twitter" are trademarks of X Corp, used here only descriptively to identify the third-party service this software interoperates with.

Why a browser instead of the API

X's official API is expensive and heavily gated. This server drives a real, undetected Chrome session via Patchright and reads the rendered page, so it works with a normal logged-in account. Selectors target X's stable data-testid attributes and will need occasional maintenance as the UI changes.

Related MCP server: tweetsave-mcp

Tools

Handles may be passed as @name, name, or a full https://x.com/name URL. Write tools require an authenticated session (run login or set X_AUTH_TOKEN). See docs/RESEARCH.md for the reverse-engineered login/post HTTP flow behind a future browserless implementation.

Roadmap

The current scope is intentionally minimal: sign in and start posting. Everything below is a TODO, modelled on the capabilities of stickerdaniel/linkedin-mcp-server (the project that inspired this one) and adapted to X.

Near-term (the current focus)

• Interactive sign-in — the login tool opens a browser for manual auth and persists the session (run with X_HEADLESS=false). Cookie auth still works.

• post_tweet(text) — publish a post from the logged-in account.

Scaffolded but not yet validated against live X — selectors and the compose DOM drift. Verify with a real session before trusting output.

Write actions (X-native, inspired by connect_with_person / send_message)

• reply_to_tweet

• quote_tweet

• like_tweet

• repost

• delete_tweet

• follow_user

• unfollow

• send_dm, get_inbox, get_conversation, search_conversations (mirrors LinkedIn's messaging tools)

Read actions

• get_my_profile — the authenticated user's own profile (get_my_profile).

• get_home_timeline — the logged-in home feed (get_feed).

• search_users — people search (search_people).

• get_who_to_follow — recommended accounts (get_sidebar_profiles).

Session & tooling

• close_session tool to terminate the browser and clean up.

• Streamable HTTP transport in addition to stdio.

• Claude Desktop one-click .mcpb bundle.

• Secure credential storage via the system keyring.

Authentication

Most X content requires a logged-in session. Two options:

Option 1: Interactive login (recommended)

uv run mcp-server-x --login

This opens a browser where you sign in manually (handles 2FA and challenges). The session is saved to X_USER_DATA_DIR (default: ~/.x-mcp/profile) and reused on all future runs — no cookie management needed.

Option 2: Manual session cookies

Set environment variables in .env (copy from .env.example):

X_AUTH_TOKEN=...   # the `auth_token` cookie from x.com
X_CSRF_TOKEN=...   # the `ct0` cookie (optional but recommended)

To grab them: log in to x.com, open DevTools → Application → Cookies → https://x.com, and copy auth_token and ct0.

Verify authentication

uv run mcp-server-x --check-auth

Clear the saved session

uv run mcp-server-x --logout

Run

With uvx, from PyPI (recommended)

Published as mcp-server-x — uvx runs it without a local install:

# one-time interactive login (opens a browser, saves the session)
uvx mcp-server-x --login

# then run the server
uvx mcp-server-x

Pin a version for reproducibility, e.g. uvx mcp-server-x@0.2.2.

With uvx, straight from GitHub

To run an unreleased commit, point uvx at the repo instead:

uvx --from git+https://github.com/afikrim/x-mcp-server.git mcp-server-x --login
uvx --from git+https://github.com/afikrim/x-mcp-server.git mcp-server-x

Pin a tag or commit for reproducibility, e.g. git+https://github.com/afikrim/x-mcp-server.git@v0.2.2.

The Chromium browser is auto-provisioned on first launch if it isn't already present, so there's no separate patchright install step. (It downloads ~150MB once into the Patchright browser cache.)

Install into an MCP client (automatic)

--install writes the config for you, merging into the client's existing servers (it never clobbers other entries) and using each client's own CLI when available:

uvx mcp-server-x --install claude-desktop
uvx mcp-server-x --install claude-code
uvx mcp-server-x --install codex
uvx mcp-server-x --install opencode

Restart the client afterward. Run --login once (see above) so the session exists before the client first calls a tool.

MCP client config (manual)

If you'd rather configure by hand:

{
  "mcpServers": {
    "mcp-server-x": {
      "command": "uvx",
      "args": ["mcp-server-x"]
    }
  }
}

No env block is needed once you've run --login — the session is read from ~/.x-mcp/profile. (You can still pass X_AUTH_TOKEN / X_CSRF_TOKEN instead.)

Local development

uv sync
uv run patchright install chromium

# Option 1: Interactive login (saves session for future runs)
uv run mcp-server-x --login

# Option 2: Run the server (with X_AUTH_TOKEN/X_CSRF_TOKEN from .env)
uv run mcp-server-x

# Check auth status
uv run mcp-server-x --check-auth

# Clear the saved session
uv run mcp-server-x --logout

CLI flags:

• --login — Open browser for interactive sign-in, save session.

• --logout — Clear the saved browser profile.

• --check-auth — Check if the session is authenticated and exit.

• --install {claude-desktop,claude-code,codex,opencode} — Register the server in a client's config and exit.

• --no-headless — Show the browser window (useful for debugging login).

• --log-level {DEBUG,INFO,WARNING,ERROR} — Set verbosity (default: INFO).

Docker

docker build -t x-mcp-server .
docker run --rm -i -e X_AUTH_TOKEN=... -e X_CSRF_TOKEN=... x-mcp-server

Configuration

All settings are environment variables (prefix X_). See .env.example for the full list: X_HEADLESS, X_USER_DATA_DIR, X_BROWSER_CHANNEL, X_NAV_TIMEOUT_MS, X_LOG_LEVEL.

Contributing

Contributions welcome — see CONTRIBUTING.md for setup, conventions (notably: data-testid selectors only, browser-driven not API), and the current feature status.

Disclaimer & responsible use

This tool is for personal and research use only, and comes with no warranty of any kind. Use it in accordance with X's Terms of Service.

Is this safe? Will I get banned?

This server controls a real, logged-in browser session — it does not exploit undocumented APIs or bypass authentication. That said, X's Terms of Service prohibit scraping and automated access without prior consent, and accounts using automated tools can be rate-limited, restricted, or banned. There is no guarantee of account safety. Use at your own risk, and prefer an account you can afford to lose.

Because the session is authenticated, you have agreed to X's terms — so the risk here is contractual (breach of the ToS) and operational (account action), not just abstract. See the LinkedIn precedent (hiQ v. LinkedIn) for how courts have treated authenticated scraping versus public-data scraping.

Keep volume sane

You are responsible for the volume of automation you run. Use it sparingly, keep pacing human-like, respect rate limits, and prompt your agents responsibly. Do not redistribute, resell, or build public datasets from the output.

For anything commercial or at scale

Use the official X API, or obtain written consent from X. The browser route is not defensible at scale — switch to a licensed path before you grow beyond personal use.

Credits

This project is directly inspired by stickerdaniel/linkedin-mcp-server by Daniel Sticker — a stealth-browser MCP server for LinkedIn. The architecture (Patchright + FastMCP, cookie/session auth, uvx distribution) and the Roadmap above follow its design. Go give it a star.

License

MIT — see LICENSE.