What is sui-mcp CLAUDE.md?

Instructions for a TypeScript MCP server that queries the Sui blockchain, a network for digital assets and applications. They describe its architecture, supported network choices, query tools, transaction decoding, token and NFT discovery, and fallback behavior.

Use them when developing, configuring, testing, or maintaining the sui-mcp server and its blockchain-query tools.

They help a developer understand where the server’s code belongs and how to choose between Sui mainnet, testnet, and devnet. They also document which transport and data clients it uses.

How 0xfreak0/sui-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 0xfreak0/sui-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/0xfreak0/sui-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/0xfreak0/sui-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/0xfreak0/sui-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/0xfreak0/sui-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/0xfreak0/sui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0xfreak0/sui-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/0xfreak0/sui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0xfreak0/sui-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8,286 This file is loaded in full into every session.

When invoked 8,286 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	$0.08286	$0.08286
Opus 5	$0.04143	$0.04143
Sonnet 5	$0.01657	$0.01657
Haiku 4.5	$0.00829	$0.00829

Measured 4d ago against content hash 5bc03374a259, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sui-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 4d 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 · 625 lines

How it starts

The opening of the file, as written. The whole thing — 625 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sui-mcp

MCP server for querying the Sui blockchain over stdio.

Stack

TypeScript (ES2022, NodeNext modules, strict mode)
@mysten/sui gRPC client + graphql-request for filtered queries
@modelcontextprotocol/sdk for MCP server framework
zod for input validation
vitest for tests

Architecture

src/
├── index.ts              # MCP server entry point (stdio transport)
├── config.ts             # Network endpoints, constants
├── clients/              # gRPC + GraphQL client setup
├── tools/                # One file per tool category (41 tools total)
├── protocols/            # Protocol registry for tx decoding
├── data/                 # Static JSON data (token registry, etc.)
├── utils/                # Shared helpers (formatting, SuiNS, etc.)
├── discovery.ts          # Token discovery (static + Aftermath fallback)
├── discovery-nft.ts      # NFT collection discovery
└── resources.ts          # MCP resources

Per-call network selection. SUI_NETWORK sets only the default (mainnet if unset); every tool also takes an optional network arg ("mainnet" | "testnet" | "devnet"), so a single session can query multiple networks (e.g. compare a testnet value to mainnet).

src/tools/with-network.ts wraps server.tool once: it injects the network arg into every tool's schema and runs each handler inside runWithNetwork(network) (an AsyncLocalStorage context in config.ts). Individual tool files are untouched.
sui / archive (grpc) and gqlQuery (graphql) are proxies over per-network client caches (getClients, getGraphqlClient). They re-resolve against getNetwork() on every access, so the same imported reference targets whichever network the active call selected. Clients are built lazily and cached per network. getNetwork() reads the async context, falling back to the default.
Never use JSON-RPC. Fullnode JSON-RPC is deprecated/removed; all on-chain reads go through gRPC (@mysten/sui/grpc) or GraphQL. @mysten/sui/client may only be imported for types (import type), never as a runtime client.

Read the full file on GitHub · 625 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.

4d ago Changed · +311 lines · +4,181 tokens per session 5bc03374a259
5d ago Changed · +215 lines · +2,907 tokens per session 429a65262c77
9d ago First seen · 99 lines · 1,198 tokens per session scan A 871f3a122353

Subscribe to this mod's changes

sui-mcp CLAUDE.md is an instructions file published in the GitHub repository 0xfreak0/sui-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 8,286 tokens to every session, about $0.0414 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 Web3 and blockchain ai-tools anthropic claude mcp mcp-server model-context-protocol

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

sui-mcp: Instructions file for Claude Code