What is mcp-devtools CLAUDE.md?

Project instructions for MCP DevTools, a modular Go server that provides developer tools through a plugin-like architecture. They document commands for building, running, testing, linting, and managing dependencies.

Use them when building or running the server, testing or linting changes, updating dependencies, or creating a new tool in its registry.

They give coding assistants the repository’s expected commands and explain where to read before changing the server or adding a new tool.

How sammcj/mcp-devtools configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sammcj/mcp-devtools. 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/sammcj/mcp-devtools/main/CLAUDE.md

Clone the repo

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

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

Your own site

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

Per session 2,867 This file is loaded in full into every session.

When invoked 2,867 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	$0.02867	$0.02867
Opus 5.5	$0.01147	$0.01147
Sonnet 5.5	$0.00573	$0.00573
Haiku 4.5	$0.00287	$0.00287

Measured 2mo ago against content hash a70a02ea90f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-devtools 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 · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 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 (claude.ai/code) when working with code in this repository.

Commands

Build and Run

make build - Build the server binary to bin/mcp-devtools
make run - Build and run server with stdio transport (default)
make run-http - Build and run server with HTTP transport on port 18080

Testing

make test - Run all tests (includes external API tests, ~10s)
make test-fast - Run tests without external API calls (~7s)
make test-verbose - Show detailed per-test timing
make test-slow - Show slowest tests sorted by duration
go test -short -v ./tests/... - Run specific test suites

Code Quality

make lint - Run linting, formatting and modernisation checks

Dependencies

make deps - Install dependencies
make update-deps - Update dependencies
go mod tidy - Clean up go.mod

Architecture

This is a modular MCP (Model Context Protocol) server built in Go that provides developer tools through a plugin-like architecture.

Please read the README.md for more information, and docs/creating-new-tools.md for details on how to create new tools.

Core Components

Tool Registry (internal/registry/) - Central registry that manages tool registration and discovery
Tool Interface (internal/tools/tools.go) - Defines the interface all tools must implement
Main Server (main.go) - MCP server that supports multiple transports (stdio, SSE, HTTP)

Tool Categories

Tools are organised into categories under internal/tools/, e.g:

internetsearch/ - Internet Search API integrations (web, image, news, video, local)
packageversions/ - Package version checking across ecosystems (npm, python, go, java, swift, docker, github-actions, bedrock, rust)
shadcnui/ - shadcn/ui component information and examples
think/ - Structured reasoning tool for AI agents
webfetch/ - Web content fetching and conversion to markdown
utils/ - Shared utilities for tools (e.g. proxy)
etc..

Read the full file on GitHub · 235 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 · 235 lines · 2,867 tokens per session scan A a70a02ea90f9

Subscribe to this mod's changes

mcp-devtools CLAUDE.md is an instructions file published in the GitHub repository sammcj/mcp-devtools (162 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,867 tokens to every session, about $0.0115 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.

LLM agentic ai cline coding devtools

mcp-devtools CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-devtools CLAUDE.mdsammcj/mcp-devtools	Instructions file	162	yesterday	Apache-2.0	A	2,867	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

mcp-devtools: Instructions file for Claude Code