What is mcp-server-qlever CLAUDE.md?

A set of Claude Code instructions for developing an MCP server that connects AI clients to QLever, a search engine for knowledge graphs using SPARQL queries. It documents the project structure, commands, technology choices, and domain rules.

Use it when building, testing, or extending the qlever MCP server, including its search, query, spatial, update, and autocomplete tools.

It gives an AI coding assistant the project-specific information needed to make compatible changes and run the right checks.

How XORwell/mcp-server-qlever configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to XORwell/mcp-server-qlever. 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/XORwell/mcp-server-qlever/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/XORwell/mcp-server-qlever

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/xorwell/mcp-server-qlever/claude-md/github.svg)](https://agentmods.dev/instructions/xorwell/mcp-server-qlever/claude-md)

Your own site

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

Per session 534 This file is loaded in full into every session.

When invoked 534 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	$0.00534	$0.00534
Opus 5	$0.00267	$0.00267
Sonnet 5	$0.00107	$0.00107
Haiku 4.5	$0.00053	$0.00053

Measured 8d ago against content hash ce9b0aeaa172, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-server-qlever 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 8d 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-server-qlever — MCP Server for QLever SPARQL Engine

Model Context Protocol server connecting Claude Code (and other MCP clients) to QLever knowledge graph endpoints. Published on npm.

Tech Stack

Runtime: Node.js >= 20, TypeScript (ES modules)
MCP SDK: @modelcontextprotocol/sdk
Validation: zod
Tests: vitest
Build: tsc (no bundler)
Package: npm (mcp-server-qlever)

Key Commands

npm run build          # tsc compile
npm run dev            # tsc --watch
npm run test           # vitest run (all tests)
npm run test:unit      # unit tests only
npm run test:integration  # needs QLever running
npm run test:ci        # spins up docker, runs unit+integration, tears down
npm run test:ci:gnd    # full test with GND dataset
npm start              # node dist/index.js

Architecture

src/
  index.ts             Entry point, MCP server setup, CLI arg parsing
  tools.ts             Core MCP tool definitions (sparql_query, search, etc.)
  advanced-tools.ts    Extended tools (spatial, update, autocomplete)
  qlever-client.ts     HTTP client for QLever API
  prompts.ts           MCP prompt templates
  format-helpers.ts    Result formatting utilities
test/
  unit/                Pure logic tests (no network)
  integration/         Tests against running QLever
  e2e/                 Full MCP protocol tests
  fixtures/            Test data
  helpers.ts           Shared test utilities
  mock-server.ts       QLever mock for unit tests
examples/
  gnd/                 German National Library dataset example

Domain Rules

All SPARQL handling must sanitize IRIs and prevent injection
New tools must follow MCP protocol spec (inputSchema with zod, proper error responses)
Keep dependencies minimal — this ships as an npm package
Docker Compose files: test.yml for CI, allinone.yml for demo, gnd.yml for real data

Do NOT

Add runtime dependencies without strong justification (ships as lightweight npm package)
Skip IRI validation or SPARQL sanitization in new tools
Break the CLI interface (-e flag for endpoint URL)
Modify test fixtures without updating corresponding test expectations
Use CommonJS imports — this is an ES module project ("type": "module")

Read the full file on GitHub · 62 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.

8d ago First seen · 62 lines · 534 tokens per session scan A ce9b0aeaa172

Subscribe to this mod's changes

mcp-server-qlever CLAUDE.md is an instructions file published in the GitHub repository XORwell/mcp-server-qlever (2 stars, last pushed 4mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0027 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 mcp mcp-server qlever sparql

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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 · 5,153 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

mcp-server-qlever: Instructions file for Claude Code