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.
npx agentmods add instructions/lreimer/sonar-mcp-server/claude-mdgit clone --depth 1 https://github.com/lreimer/sonar-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/lreimer/sonar-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/lreimer/sonar-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/lreimer/sonar-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00734 | $0.00734 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
sonar-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
Sonar MCP Server is a Go implementation of an MCP (Model Context Protocol) server for integrating with the SonarQube Cloud API. It's designed to be used with Claude and other AI assistants to provide information about SonarQube projects, issues, hotspots, and code duplications.
Commands
Build and Run
# Basic build
make build
# or
go build -ldflags "-X main.version=$(git describe --tags --always --dirty)"
# Clean build artifacts
make clean
# Quick snapshot build with goreleaser
goreleaser build --snapshot --clean
# Create a snapshot release with goreleaser
goreleaser release --skip=publish --snapshot --clean
# Run as stdio binary (default)
./sonar-mcp-server -t stdio
# Run as SSE server
./sonar-mcp-server -t sse -p 8080 -b http://localhost:8080
Testing
# Run all tests
go test ./...
# Run tests for a specific package
go test ./sonar
# Run a specific test
go test ./sonar -run TestUnmarshalProjectsResponse
# Run tests with verbose output
go test -v ./...
Environment Setup
The server requires a SonarQube API token to be set as an environment variable:
export SONAR_TOKEN="your-sonar-token"
Architecture
The codebase follows a simple modular structure:
-
Main Package (
main.go): Entry point that sets up the MCP server with the appropriate transport (stdio or SSE) and registers all the Sonar API tools. -
Sonar Package (
sonar/): Contains all the functionality for interacting with the SonarQube API:types.go: Defines data structures for SonarQube API responsesprojects.go: Tool for listing SonarQube projectsissues.go: Tool for searching and retrieving project issueshotspots.go: Tool for working with security hotspotsduplications.go: Tool for code duplication detectionsecurity.go: Handles token securityutils.go: Common utility functions for HTTP requests and response formatting
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.
- 5d ago First seen · 97 lines · 734 tokens per session scan A e9c1c93c07dc
sonar-mcp-server CLAUDE.md is an instructions file published in the GitHub repository lreimer/sonar-mcp-server (2 stars, last pushed 1y ago), licensed MIT. It adds 734 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
sonarqube-mcp-server AGENTS.md
AGENTS.md instructions for SonarSource/sonarqube-mcp-server, covering sonarqube mcp server, principles, prerequisites, build & verify and code style.
sonarlint-mcp-server CLAUDE.md
Instructions for nielspeter/sonarlint-mcp-server, covering claude code development guide, release process, how versioning works, important: do not manually edit changelog.md and configuration files.
sonarqube-mcp AGENTS.md
AGENTS.md instructions for metalralf/sonarqube-mcp, covering agents.md — sonarqube mcp server, ⚠️ critical rules — read before any work, every handler → must have a test, every commit → must pass these first and every new language scan → must update langconfigs.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.