What is semrush-mcp CLAUDE.md?

Project guidance for Semrush MCP, a server and command-line tool that provides Semrush data for keyword research, website analysis, backlinks, traffic, and competitor research. MCP is a standard way for AI clients to call external tools.

Use it when developing or checking the Semrush server or CLI, running unit or integration tests, validating TypeScript, or working with its Git hooks.

It clarifies how to install, build, test, lint, format, and publish the project while separating tests that need an API key from those that do not.

How mrkooblu/semrush-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrkooblu/semrush-mcp. 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/mrkooblu/semrush-mcp/main/CLAUDE.md

Clone the repo

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

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/mrkooblu/semrush-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mrkooblu/semrush-mcp/claude-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mrkooblu/semrush-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mrkooblu/semrush-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 920 This file is loaded in full into every session.

When invoked 920 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	$0.00920	$0.00920
Opus 5.5	$0.00368	$0.00368
Sonnet 5.5	$0.00184	$0.00184
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash 4fab2a618635, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

semrush-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 2mo 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with code in this repository.

Project Overview

semrush-mcp is a unified Semrush MCP server and CLI for keyword research, domain analytics, backlinks, traffic analysis, and competitive intelligence. It provides two entry points that share the same API client:

semrush-mcp — MCP server (stdio transport) for AI clients (Claude, Cursor, etc.)
semrush — CLI for direct terminal usage

Commands

# Development
npm install          # Install dependencies
npm run build        # Build TypeScript to dist/
npm run dev          # Start MCP server in dev mode (tsx)
npm run start        # Start built MCP server

# Testing
npm test             # Run all tests
npm run test:unit    # Unit tests only (mocked, no API key needed)
npm run test:integration  # Integration tests (requires SEMRUSH_API_KEY)

# Quality
npm run lint         # ESLint
npm run format       # Prettier format

Git Hooks

Pre-commit and pre-push hooks are installed via Husky.

Pre-commit runs:

lint-staged (prettier + eslint auto-fix on staged .ts files)
ESLint (full lint pass)
TypeScript type-check (tsc --noEmit)
Unit tests (excludes integration tests)
Secret detection (scans for hardcoded API keys/tokens)

Pre-push runs:

Uncommitted changes check
Full build (npm run build)
Integration tests (requires SEMRUSH_API_KEY)

Architecture

src/
├── index.ts          # MCP server entry point (McpServer API)
├── cli.ts            # CLI entry point (Commander.js)
├── semrush-api.ts    # Shared API client (singleton via lazy Proxy)
├── schemas.ts        # Zod validation schemas + inferred TS types
├── config.ts         # Configuration, logger, env loading
└── __tests__/        # Test suite (unit + integration)

Key patterns:

semrushApi is a lazy Proxy singleton — import it, never construct SemrushApiClient directly (except in tests)
The API client handles retries (429/5xx), caching, and rate limiting internally
SemrushApiError has .status and .response fields for error handling

Read the full file on GitHub · 105 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.

2mo ago First seen · 105 lines · 920 tokens per session scan A 4fab2a618635

Subscribe to this mod's changes

semrush-mcp CLAUDE.md is an instructions file published in the GitHub repository mrkooblu/semrush-mcp (40 stars, last pushed 1mo ago), licensed MIT. It adds 920 tokens to every session, about $0.0037 per session on Opus 5.5. 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 2026-08-30.

Analytics and metrics Marketing and SEO

semrush-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
semrush-mcp CLAUDE.mdmrkooblu/semrush-mcp	Instructions file	40	1mo ago	MIT	A	920	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

semrush-mcp: Instructions file for Claude Code