substrate-mcp: Instructions file for Claude Code

CLAUDE.md

substrate-mcp CLAUDE.md is an instructions file for Claude Code from Moonsong-Labs/substrate-mcp. It costs 1,930 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a Rust-based MCP server that will provide tools for Substrate blockchains. Rust is a programming language, and Substrate is a framework for building blockchains.

In plain words
What is it for?
Use them when developing or extending the server, especially its Rust service, prompt modules, release-impact analysis, and getting-started functionality described in the project files.
Why use it?
They give an AI coding assistant the repository's structure, development context, and expected build guidance. This helps work stay aligned with a project that is currently early-stage scaffolding.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Moonsong-Labs/substrate-mcp's own configuration. It tells Claude Code how to work on substrate-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 substrate-mcp configures →

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/moonsong-labs/substrate-mcp/claude-md.svg)](https://agentmods.dev/instructions/moonsong-labs/substrate-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/moonsong-labs/substrate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/moonsong-labs/substrate-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,930 This file is loaded in full into every session.
When invoked 1,930 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 $0.01930 $0.01930
Opus 5 $0.00965 $0.00965
Sonnet 5 $0.00386 $0.00386
Haiku 4.5 $0.00193 $0.00193

Measured 6d ago against content hash cdb15ff172ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

substrate-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 6d 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 · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 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

This is a Rust-based MCP (Model Context Protocol) server designed to provide tools for working with Substrate-based blockchains. The project is in early development (v0.1.0) and currently contains scaffolding for future Substrate-specific functionality.

Repository Structure

substrate-mcp/
├── Cargo.toml          # Project manifest with dependencies
├── Cargo.lock          # Dependency lock file
├── LICENSE             # Project license
├── README.md           # User-facing documentation with installation/usage instructions
├── CLAUDE.md           # This file - development guidance
└── src/
    ├── main.rs         # Entry point with tokio async runtime
    └── service/        # MCP service implementation
        ├── mod.rs      # Main service with tool and prompt routing
        ├── prompts/    # MCP prompt templates
        │   ├── mod.rs                      # Prompt module registry
        │   ├── analyze_release.rs          # Release impact analysis
        │   ├── get_started.rs              # Getting started guide
        │   ├── release_comparison.rs       # Release comparison
        │   ├── scaffold_pallet.rs          # Pallet scaffolding
        │   ├── security_review.rs          # Security review (merged from multiple security prompts)
        │   └── common.rs                   # Common prompt utilities
        ├── resources/  # MCP resources (documentation, references)
        ├── tools/      # MCP tools implementation
        └── utils.rs    # Service utilities

## Development Commands

### Build
```bash
cargo build

Run

cargo run

Test

cargo test

Lint and Format

cargo clippy
cargo fmt

Dependencies

  • rmcp (v0.3.0): MCP server framework with transport-io feature
  • tokio (v1): Async runtime with full features
  • serde (v1): Serialization/deserialization with derive feature
  • serde_json (v1): JSON support
  • anyhow (v1): Error handling
  • handlebars (v6): Template engine for prompt generation

Architecture

Core Structure

  • src/main.rs: Entry point that initializes the MCP server with stdin/stdout transport using tokio async runtime
  • src/service/mod.rs: Implements SubstrateService with MCP tool and prompt routing using the rmcp crate

MCP Server Pattern

This server follows the standard MCP communication pattern:

  • Uses stdin/stdout for transport (tokio's stdin/stdout)
  • Tools are defined using the #[tool] macro from rmcp
  • Prompts are defined as SubstratePromptDefinition structs with Handlebars templates
  • Server handler implemented via #[tool_handler] macro
  • Tool routing via #[tool_router] macro
  • Prompt routing via handle_list_prompts and handle_get_prompt functions

Current State

The server currently has:

  • Basic MCP server infrastructure set up
  • Multiple functional tools for blockchain interaction:
    • fetch_and_analyze_release: Fetches and analyzes Polkadot SDK releases (downloads PRDocs and generates summaries)
    • subxt_execute: Execute subxt commands for blockchain exploration
    • filter_metadata: Filter and search chain metadata
    • query_extrinsics: Query extrinsics from blocks
    • query_events: Query events from blocks
    • query_storage: Query chain storage entries
    • list_pallet_storage: List storage entries in a pallet
    • submit_dev_extrinsic: Submit extrinsics using dev accounts
  • Current prompt templates for Substrate development:
    • release_comparison: Compare changes between Polkadot SDK versions
    • analyze_release: Analyze how releases impact your project
    • scaffold_pallet: Generate pallet implementation scaffolding
    • security_review: Comprehensive security review covering code security, economic threats, and performance analysis
    • get_started: Get started guide for Substrate/Polkadot development
  • Server info indicating it's for Substrate-based blockchain development
  • Tools, resources, and prompts capabilities enabled
  • Server name: "substrate-mcp" (version 0.1.0)

Prompt System Architecture

The server uses a modular prompt template system built with Handlebars:

Prompt Structure

Each prompt module follows this pattern:

use handlebars::Handlebars;
use rmcp::model::{PromptMessage, PromptMessageRole};
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use serde_json::json;

Read the full file on GitHub · 211 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. 6d ago First seen · 211 lines · 1,930 tokens per session scan A cdb15ff172ef

Subscribe to this mod's changes

substrate-mcp CLAUDE.md is an instructions file published in the GitHub repository Moonsong-Labs/substrate-mcp (5 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,930 tokens to every session, about $0.0097 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.

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 · 5,182 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