BNB Chain MCP server connection and tool usage. Covers npx @bnb-chain/mcp@latest, PRIVATE_KEY and RPC, and every MCP tool — blocks, transactions, contracts, ERC20/NFT transfers, wallet, ERC-8004 agent registration, Greenfield. Use when connecting to bnbchain-mcp, querying or transacting on BNB Chain/opBNB/EVM, registering as ERC-8004 agent, or using Greenfield.
npx skills add https://github.com/internet-court/internet-court-skill --skill bnbchain-mcp
How to connect to the BNB Chain MCP server and use its tools: blocks, transactions, contracts, tokens, NFTs, wallet, ERC-8004 agents, and Greenfield. Use this skill when working with BNB Chain / opBNB / EVM or Greenfield via MCP.
npx @bnb-chain/mcp@latest (fetches from npm at runtime). Source: github.com/bnb-chain/bnbchain-mcp.env for state-changing tools (transfers, write_contract, approve_token_spending, ERC-8004 register/set_uri, Greenfield writes). Never log or expose private keys.PRIVATE_KEY in the server environment.Add the bnbchain-mcp server to the MCP client config (e.g. Cursor MCP settings, Claude Desktop claude_desktop_config.json).
Default (stdio):
{
"mcpServers": {
"bnbchain-mcp": {
"command": "npx",
"args": ["-y", "@bnb-chain/mcp@latest"],
"env": {
"PRIVATE_KEY": ""
}
}
}
}
SSE mode: "args": ["-y", "@bnb-chain/mcp@latest", "--sse"] (and client SSE URL if required). Local dev server (e.g. bun dev:sse in bnbchain-mcp): "url": "http://localhost:3001/sse" with the same env.
Restart or reload the MCP client after changing config so the server starts.
env when state-changing tools are needed; leave empty for read-only. Do not commit or echo keys.register_erc8004_agent (see references/erc8004-tools-reference.md).network is optional; default is bsc. Use get_supported_networks to list options.transfer_native_token, transfer_erc20, transfer_nft, transfer_erc1155, approve_token_spending, write_contract, register_erc8004_agent, set_erc8004_agent_uri, Greenfield writes): network is REQUIRED. There is no default for writes. If the user does not specify the network, you MUST ask before calling the tool. Do not assume or default to mainnet (bsc); accidental mainnet execution causes irreversible financial loss.| Category | Examples | Needs PRIVATE_KEY? |
|----------|----------|--------------------|
| Blocks | get_latest_block, get_block_by_number, get_block_by_hash | No |
| Transactions | get_transaction, get_transaction_receipt, estimate_gas | No (estimate only) |
| Network | get_chain_info, get_supported_networks | No |
| Wallet / balance | get_native_balance, get_erc20_balance, get_address_from_private_key | Balance: optional address or privateKey |
| Transfers / writes | transfer_native_token, transfer_erc20, transfer_nft, transfer_erc1155, approve_token_spending, write_contract | Yes |
| Contracts | read_contract, is_contract | No for read |
| Tokens / NFT | get_erc20_token_info, get_nft_info, get_erc1155_token_metadata, check_nft_ownership, get_nft_balance, get_erc1155_balance | No for read |
| ERC-8004 | register_erc8004_agent, set_erc8004_agent_uri, get_erc8004_agent, get_erc8004_agent_wallet | Register/set_uri: Yes |
| Greenfield | gnfd_* bucket/object/payment tools | Writes: Yes |
Use the MCP prompt names when the user wants analysis or guidance:
For parameter names, examples, and detailed usage of each tool, use:
| Reference | Content |
|-----------|---------|
| references/evm-tools-reference.md | Blocks, transactions, network, wallet, contracts, tokens, NFT — all EVM tools |
| references/erc8004-tools-reference.md | register_erc8004_agent, set_erc8004_agent_uri, get_erc8004_agent, get_erc8004_agent_wallet |
| references/greenfield-tools-reference.md | Buckets, objects, folders, payment accounts — all Greenfield tools |
| references/prompts-reference.md | All MCP prompts and when to use them |
transfer_*, write_contract, or approve_token_spending, confirm recipient, amount, and network before calling the tool.write_contract, approve_token_spending, ERC-8004 register/set_uri), you MUST have an explicit network from the user. If not specified, ask — do not default to mainnet. Do not use advisory language like "prefer testnet" as a substitute; the constraint is: no network specified → do not call the write tool until the user confirms.env; never in chat or logs.npx @bnb-chain/mcp@latestBuild professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract, normalize, and standardize financial data into investment committee-ready Excel workbooks with consistent structure, proper formatting, and documented assumptions. Use for M&A due diligence, private equity analysis, investment committee materials, and standardizing financial reporting across portfolio companies. Do not use for simple financial calculations or working with already-completed data packs.
| Skill that analyzes 18-month scenarios from a news headline. Runs the primary analysis with the scenario-analyst agent and obtains a second opinion with the strategy-reviewer agent. Generates a comprehensive English report covering 1st/2nd/3rd-order impacts, recommended stocks, and a critical review. medium-to-long-term investment strategy
Analyze skill library to identify coverage gaps, redundant overlaps, optimization opportunities, and provide recommendations for skill portfolio improvement
> Use this skill when the user is doing hands-on DOCA SHA programming — offloading SHA-1, SHA-256, or SHA-512 hashing onto a BlueField DPU or ConnectX accelerator, picking between one-shot `doca_sha_task_hash` and incremental `doca_sha_task_partial_hash`, querying `doca_sha_cap_*` for algorithm support and min destination / max source buffer sizes, setting source / destination `doca_mmap` permissions, or decoding DOCA_ERROR_* returns from the SHA API. Trigger even when the user does not explicitly mention "DOCA SHA" or "doca_sha_task" — typical implicit phrasings include "hash a multi-GiB file on the DPU", "offload SHA-256 to the BlueField", "streaming hash over chunks", "partial hash returns BAD_STATE", "destination buffer too small for digest", or "is SHA-512 available on this card". Refuse and route elsewhere for general cryptographic-hash theory (collision resistance, SHA-3 selection), other DOCA crypto libraries (AES-GCM, Compress, DMA), or DOCA install / BFB bring-up — those belong to other skills.
Agent skill for agentic-payments - invoke with $agent-agentic-payments
>- Onchain OS onboarding and guide hub for first-time use, product introductions, OKX.AI, and customer-support intents. Classifies requests and routes them through the Intent Routing table. Use for questions about what Onchain OS is, what it can do, getting started, tutorials, onboarding, first-time setup, and introductions; for OKX.AI explanations and role-registration routing across User, ASP, and Evaluator roles, including spelling and language variants; and for Help Center, customer service, complaints, feedback, bug reports, FAQs, or user-guide requests. Do not use for direct on-chain actions such as swaps, wallet, balance, or token operations, or for Agent task lifecycle actions such as publish, accept, deliver, or dispute; those have dedicated skills.
> Analyze a blockchain transaction by its hash using TRES Finance MCP and generate a visual flow diagram showing all asset movements, followed by a plain-language explanation of what happened. Use this skill whenever the user provides a transaction hash and asks to "analyze", "explain", "visualize", "diagram", "show me what happened in", or "tell the story of" a transaction. Also trigger when the user pastes a tx hash (long hex string starting with 0x) and asks anything about it. Always use this skill for transaction hash analysis — do not attempt to answer from memory alone.
Tracks LLM token consumption and usage metrics for billing, monitoring, and optimization. Use this to log token usage, calculate costs, generate invoices, and understand which agents or users consume the most resources.
Take internet-court/bnbchain-mcp from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npx.
Without those the skill loads but fails at the first command.