What is mcp CLAUDE.md?

A setup and usage guide for connecting the FourA MCP to Claude Desktop, Claude Code, or the Claude API. MCP is a way for an AI client to connect to external tools and services.

Use it when installing FourA in Claude, choosing a local or hosted connection, configuring authentication, or checking what the available FourA tools provide.

It removes uncertainty about where to put the API key, which connection command or configuration to use, and how to avoid configuration being overwritten. It also notes a client compatibility issue for large outputs.

mcp CLAUDE.md — Instructions file by fouradata

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/fouradata/mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/fouradata/mcp

Per session 439 This file is loaded in full into every session.

When invoked 439 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00439	$0.00439
Opus 5	$0.00219	$0.00219
Sonnet 5	$0.00088	$0.00088
Haiku 4.5	$0.00044	$0.00044

Measured 2d ago against content hash 6cea70200b71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp 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 2d 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 · 52 lines

What it actually says

Using the FourA MCP with Claude

Setup notes specific to Claude Desktop, Claude Code, and the Claude API. For the full tool and prompt reference see README.md and AGENTS.md.

Claude Code

export FOURA_API_KEY=pk_live_...
claude mcp add foura -- npx -y @fouradata/mcp

Or connect to the hosted endpoint (Streamable HTTP):

claude mcp add --transport http foura https://mcp.foura.ai/mcp --header "Authorization: Bearer pk_live_..."

Claude Desktop

Add this to claude_desktop_config.json (Settings -> Developer -> Edit Config):

{
  "mcpServers": {
    "foura": {
      "command": "npx",
      "args": ["-y", "@fouradata/mcp"],
      "env": { "FOURA_API_KEY": "pk_live_..." }
    }
  }
}

Gotcha: fully quit Claude Desktop (Cmd+Q on macOS) before editing the config. If it is still running, it overwrites your edits with its in-memory config on exit. Use the stdio config above for Claude Desktop; remote transport support varies by client version.

offload_large requires a client that can read MCP resource_link blocks. Leave it at the default false if your client doesn't support them.

What you get

Four tools (foura_auto, foura_single, foura_proxy, foura_browser) and six prompts under /prompts. All tools are read-only, so Claude clients that auto-approve trusted read-only tools call them without a per-request confirmation prompt. Start with foura_auto - give it a URL and it returns the page, choosing the fetch method for you.

FourA: https://foura.ai | MCP server: https://foura.ai/mcp | Docs: https://foura.ai/docs/mcp/server

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.

2d ago First seen · 52 lines · 439 tokens per session scan A 6cea70200b71

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository fouradata/mcp (4 stars, last pushed 13d ago), licensed MIT. It adds 439 tokens to every session, about $0.0022 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.

Backend and APIs Browser automation Data and AI ai-agents claude mcp model-context-protocol typescript web-scraping

mcp CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Using the FourA MCP with Claude

Claude Code

Claude Desktop

What you get

What this file has done since we first saw it

Other instructions, from other repositories

BraveMCP CLAUDE.md

helm CLAUDE.md

qutebrowser-mcp CLAUDE.md

OneJS AGENTS.md

AutomatiQ AGENTS.md

ketch CLAUDE.md