What is x-mcp-server CLAUDE.md?

Repository instructions for an MCP server that reads and writes X, formerly known as Twitter, through a logged-in Chrome browser. They describe its Python stack, commands, architecture, and coding conventions.

Working on authentication, browser automation, X content operations, dependencies, linting, and local server commands.

They give coding agents the project rules and setup details needed to change and validate the server consistently.

How afikrim/x-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to afikrim/x-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/afikrim/x-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/afikrim/x-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/afikrim/x-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/afikrim/x-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/afikrim/x-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/afikrim/x-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,148 This file is loaded in full into every session.

When invoked 1,148 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01148	$0.01148
Opus 5	$0.00574	$0.00574
Sonnet 5	$0.00230	$0.00230
Haiku 4.5	$0.00115	$0.00115

Measured 7d ago against content hash 4b2c42e4f5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

x-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

x-mcp-server

A stealth-browser MCP server that reads and writes content on X (formerly Twitter) and exposes it over FastMCP. It drives an undetected Chrome via Patchright and operates the rendered DOM, so it works with a normal logged-in account instead of the paid X API. Inspired by stickerdaniel/linkedin-mcp-server.

Designed to run via uvx straight from GitHub, so any MCP client can launch it with no local setup.

Stack

Python >= 3.11, packaged with hatchling, dependency/run via uv
fastmcp for the MCP layer (stdio transport)
patchright (undetected Playwright fork) for the browser
pydantic / pydantic-settings for models and config

Commands

uv sync                              # install deps into .venv
uv run patchright install chromium   # one-time browser download (auto on first run too)

uv run mcp-server-x --login          # interactive sign-in; saves to ~/.x-mcp/profile
uv run mcp-server-x --check-auth     # verify the session is valid
uv run mcp-server-x                  # run the server over stdio
uvx --from . mcp-server-x            # run from a checkout without installing

uv run ruff check .                  # lint (must pass)
uv run ruff format .                 # format
uv run pytest                        # tests (none yet)

Architecture

x_mcp_server/server.py — builds the FastMCP instance, registers tools, defines check_auth. Module-level mcp is the entry object.
x_mcp_server/__main__.py — the mcp-server-x console script (CLI): --login, --logout, --check-auth, --install, --no-headless; with no flag it runs mcp.run() over stdio. CLI auth commands close the browser cleanly inside the event loop.
x_mcp_server/browser.py — BrowserSession singleton: one persistent Patchright context, launched lazily and reused. Injects auth_token/ct0 cookies, detects the /login wall, retries transient network errors with backoff, and auto-provisions Chromium when missing.
x_mcp_server/extract.py — DOM extraction. Runs JS in the page via page.evaluate, targets stable data-testid selectors. This is the most fragile code in the repo.
x_mcp_server/config.py — Settings from X_* env vars (and .env). user_data_dir defaults to ~/.x-mcp/profile; a validator expands ~ and $VAR.
x_mcp_server/install.py — --install writers for Claude Desktop, Claude Code, Codex, OpenCode (merge into existing config; prefer the client's CLI when present).
x_mcp_server/tools/ — one module per capability (profile, timeline, search, auth, post), wired in tools/__init__.py:register. _common.collect_tweets handles scroll pagination.

Read the full file on GitHub · 61 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 61 lines · 1,148 tokens per session scan A 4b2c42e4f5aa

Subscribe to this mod's changes

x-mcp-server CLAUDE.md is an instructions file published in the GitHub repository afikrim/x-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,148 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

x-mcp-server: Instructions file for Claude Code