What is mcp-klever-vm CLAUDE.md?

A project guide for developing an MCP server for Klever blockchain smart contracts. MCP, or Model Context Protocol, lets coding tools connect to outside knowledge and services.

It is for installing dependencies, building, testing, linting, formatting, running the HTTP or MCP server, and loading knowledge into Redis.

It gives an unfamiliar developer the project overview, architecture, commands, testing setup, and ways to run the server.

How klever-io/mcp-klever-vm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to klever-io/mcp-klever-vm. 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/klever-io/mcp-klever-vm/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/klever-io/mcp-klever-vm

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/klever-io/mcp-klever-vm/claude-md/github.svg)](https://agentmods.dev/instructions/klever-io/mcp-klever-vm/claude-md)

Your own site

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

Per session 1,840 This file is loaded in full into every session.

When invoked 1,840 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	$0.01840	$0.01840
Opus 5	$0.00920	$0.00920
Sonnet 5	$0.00368	$0.00368
Haiku 4.5	$0.00184	$0.00184

Measured 11d ago against content hash f8a21be4757a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-klever-vm 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 11d 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 · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 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.

Project Overview

MCP (Model Context Protocol) server for Klever blockchain smart contract development. Provides contextual knowledge management (95+ entries across 11 categories) for developers working with the Klever VM SDK (Rust). Runs in two modes: HTTP API server (Express) or MCP protocol server (stdio transport).

Common Commands

pnpm install                    # Install dependencies
pnpm run build                  # Build (tsc + copy templates to dist/)
pnpm run dev                    # Dev mode with watch (HTTP server)
pnpm run dev:mcp                # Dev mode with watch (MCP server, memory storage)
pnpm test                       # Run tests (Jest with ESM via --experimental-vm-modules)
pnpm run lint                   # Lint with ESLint
pnpm run format                 # Format with Prettier
pnpm run ingest                 # Ingest knowledge base into Redis storage
MODE=mcp pnpm start             # Run as MCP server (production)

Tests use Jest with ESM support. The test command is node --experimental-vm-modules $(pnpm bin)/jest. Test files use .test.ts extension and match **/?(*.)+(spec|test).ts or **/__tests__/**/*.ts.

Architecture

Data Flow

The server bootstraps in src/index.ts which selects between HTTP and MCP mode based on MODE env var. Both modes share the same pipeline:

StorageFactory creates a StorageBackend (memory or Redis)
ContextService wraps storage with business logic (validation, relevance scoring, querying)
On memory storage, autoIngestKnowledge() loads all entries from src/knowledge/ at startup
HTTP mode mounts Express routes via createRoutes(contextService) at /api
MCP mode creates KleverMCPServer using @modelcontextprotocol/sdk with stdio transport

Key Interfaces

StorageBackend (src/types/index.ts): Core interface for store/retrieve/query/update/delete/count operations. All schemas defined with Zod.
ContextPayload: The main data type — has type (enum of 8 context types), content, metadata (title, tags, relevanceScore, etc.), and relatedContextIds.
KnowledgeEntry (src/knowledge/types.ts): Internal format for knowledge base entries, converted to ContextPayload during ingestion.

Read the full file on GitHub · 133 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.

11d ago First seen · 133 lines · 1,840 tokens per session scan A f8a21be4757a

Subscribe to this mod's changes

mcp-klever-vm CLAUDE.md is an instructions file published in the GitHub repository klever-io/mcp-klever-vm (31 stars, last pushed 3mo ago), licensed MIT. It adds 1,840 tokens to every session, about $0.0092 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 2026-08-30.

blockchain klever mcp mcp-server model-context-protocol smart-contracts

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-klever-vm: Instructions file for Claude Code