bnbchain-mcp: Instructions file for Claude Code

CLAUDE.md

bnbchain-mcp CLAUDE.md is an instructions file for Claude Code from bnb-chain/bnbchain-mcp. It costs 1,928 tokens per session, scanned A, original, MIT.

A project guide for BNBChain MCP, a server that lets AI assistants call tools for BNB Chain blockchain networks and Greenfield storage. It documents the TypeScript codebase, its modules, supported connection methods, and development commands.

In plain words
What is it for?
Use it when developing, building, testing, formatting, or running the BNBChain MCP server and its EVM or Greenfield tools.
Why use it?
It explains where blockchain, storage, transfer-confirmation, and server code belong, reducing guesswork when changing the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is bnb-chain/bnbchain-mcp's own configuration. It tells Claude Code how to work on bnbchain-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bnbchain-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bnb-chain/bnbchain-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/bnb-chain/bnbchain-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bnb-chain/bnbchain-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.

agentmods badge for bnbchain-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bnb-chain/bnbchain-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/bnb-chain/bnbchain-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bnb-chain/bnbchain-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bnb-chain/bnbchain-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.

agentmods 80×15 button for bnbchain-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bnb-chain/bnbchain-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bnb-chain/bnbchain-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,928 This file is loaded in full into every session.
When invoked 1,928 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01928 $0.01928
Opus 5 $0.00964 $0.00964
Sonnet 5 $0.00386 $0.00386
Haiku 4.5 $0.00193 $0.00193

Measured 9d ago against content hash 3e7376cd31ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bnbchain-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 9d 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 · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bnbchain-mcp

Project Overview

BNBChain MCP is a Model Context Protocol server that exposes BNB Chain blockchain operations as AI-callable tools. It supports two transport modes: stdio (default — local dev, IDE integrations, Claude Desktop) and SSE (HTTP + Server-Sent Events, port 3001). Three top-level modules handle EVM-compatible chains (evm), BNB Greenfield storage (gnfd), and a transfer preview-then-confirm flow (confirm).

Tech Stack

  • Runtime: Bun. Source is ESM; build output is CJS (bun build --format cjs).
  • Language: TypeScript 5.x
  • Blockchain: viem 2.x (EVM), @bnb-chain/greenfield-js-sdk 2.x (Greenfield)
  • MCP: @modelcontextprotocol/sdk 1.x
  • HTTP (SSE mode): Express 4.x + cors
  • Validation: Zod 3.x
  • Lint/format: Biome (no Prettier, no ESLint)
  • Tests: bun:test (no Jest, no Vitest)

Architecture

src/
  evm/          # EVM-compatible chains (BSC, ETH, Polygon, …)
    chains.ts   # chainMap (by ID) and networkNameMap (by name)
    modules/    # blocks, contracts, network, nft, tokens, transactions, wallet
    services/
      clients.ts  # viem clients cached by chain ID — always reuse, never ad-hoc
  gnfd/         # BNB Greenfield storage & payment
  confirm/      # pendingTransferStore (5-min TTL), confirm_transfer tool
  server/
    base.ts     # registers all module tools via register*() exports
  utils/
  index.ts      # entrypoint; selects stdio or SSE transport
e2e/            # E2E tests using MCPClient from e2e/util.ts

Key patterns:

  • MCP tool registration: each module exports a register* function called in src/server/base.ts.
  • Transfer confirmation: write tools return a confirmToken + preview; confirm_transfer executes on approval. Controlled by BNBCHAIN_MCP_SKIP_TRANSFER_CONFIRMATION.
  • Chain lookup: use chainMap (by chain ID) or networkNameMap (by name string) from src/evm/chains.ts.
  • Internal path alias: @/*src/* (defined in tsconfig.json).

Key environment variables (see .env.example):

  • PRIVATE_KEY — wallet private key (optional; required for write ops)
  • PORT — HTTP port for SSE mode (default: 3001)
  • LOG_LEVELDEBUG / INFO / WARN / ERROR
  • BNBCHAIN_MCP_SKIP_TRANSFER_CONFIRMATION — skip confirm flow (default: false)

Read the full file on GitHub · 184 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.

  1. 9d ago First seen · 184 lines · 1,928 tokens per session scan A 3e7376cd31ed

Subscribe to this mod's changes

bnbchain-mcp CLAUDE.md is an instructions file published in the GitHub repository bnb-chain/bnbchain-mcp (60 stars, last pushed 4mo ago), licensed MIT. It adds 1,928 tokens to every session, about $0.0096 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.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens