広告掲載
MCP.so
ログイン

metacontract MCP Server

@metacontract

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

metacontract

投稿者

kai hiroi

metacontract MCP Server について

A Model Context Protocol (MCP) server for metacontract smart contract development.

#smart-contract#evm#metacontract#foundry#mcp

metacontract MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mc-mcp": {
      "command": "mc-mcp",
      "env": {
        "MC_PROJECT_ROOT": "/path/to/your/project"
      }
    }
  }
}

metacontract MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is metacontract mcp?

mc-mcp is an extensible MCP server for the metacontract (mc) framework. It enables AI-powered smart contract development workflows via Foundry integration and semantic documentation search, exposing tools for project setup, testing, deployment, and documentation retrieval.

How to use metacontract mcp?

Install via cargo install mc-mcp, add the server to your MCP client (e.g., Cursor, Cline, RooCode) with MC_PROJECT_ROOT set to your project directory. The server automatically starts and provides tools like mc_search_docs_semantic, mc_setup, mc_test, mc_deploy, and mc_upgrade. An optional mcp_config.toml file under the project root customizes reference sources and script paths.

Key features of metacontract mcp

  • Layered (onion) architecture for maintainability
  • Rust implementation for performance and safety
  • Embedded Qdrant vector DB for fast semantic search
  • Local embedding generation via fastembed-rs
  • Markdown parsing for documentation indexing
  • Prebuilt documentation index auto-downloaded from GitHub Releases

Use cases of metacontract mcp

  • Initialize a new Foundry project with the metacontract template
  • Perform semantic search over mc, Solidity, and user documentation
  • Run TDD cycles: write tests and execute mc_test via your agent
  • Deploy or upgrade contracts using scripts defined in mcp_config.toml
  • Calculate ERC-7201 namespaced storage slots

よくある質問

1

What is `MC_PROJECT_ROOT` and why is it required?

`MC_PROJECT_ROOT` is an environment variable specifying the project root directory. It is required because path resolution is delegated to the MCP client, ensuring consistent behavior across environments. If unset or non-existent, the server returns an error.

2

How do I configure reference sources and scripts?

Place a `mcp_config.toml` file in your `MC_PROJECT_ROOT` directory. It defines documentation sources (local paths) and default Foundry scripts for deploy/upgrade. If the file is missing, mc-mcp uses built-in defaults.

3

What MCP transports are supported and how is authentication handled?

mc-mcp uses stdio transport (as shown in client configurations). No authentication mechanism is documented.

4

Where does the documentation index data live?

On first startup, the prebuilt documentation index (`prebuilt_index.jsonl.gz`) is downloaded from the latest GitHub Release and cached in the system cache directory. The path can be overridden in `mcp_config.toml` via `prebuilt_index_path`.

5

Are there any known runtime limits or dependencies?

The server requires Rust, Foundry (for test/deploy tools), and an MCP-compatible client. Tests may hit OS file descriptor limits (`ulimit -n 4096` recommended) or embedding model cache lock errors—these can be resolved with `make clean-cache` and single-threaded test execution.

コメント

「その他」の他のコンテンツ

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K
広告掲載