tolk-mcp-server
Enables LLMs to compile and verify Tolk smart contract code for the TON blockchain.
README
Tolk MCP Server
A Model Context Protocol (MCP) server for the Tolk compiler, enabling Large Language Models (LLMs) to compile and verify Tolk smart contract code for the TON blockchain.
Overview
This MCP server exposes the Tolk compiler functionality to AI assistants, allowing them to:
- ✅ Compile Tolk source code in real-time
- ✅ Verify code correctness before deployment
- ✅ Get compiled bytecode (BOC) and code hash
- ✅ Debug compilation errors with detailed messages
- ✅ Support multi-file projects
Supported Platforms
| Platform | Transport | Status |
|---|---|---|
| Claude Desktop | stdio | ✅ Supported |
| ChatGPT | HTTP/SSE | ✅ Supported |
| Other MCP Clients | Both | ✅ Supported |
Quick Start
Installation
# Install globally
npm install -g tolk-mcp-server
# Or install as project dependency
npm install tolk-mcp-server
# Or run directly with npx
npx tolk-mcp-server
For Claude Desktop
Add to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"tolk-compiler": {
"command": "npx",
"args": ["tolk-mcp-server"]
}
}
}
For ChatGPT
- Start the HTTP server:
npx tolk-mcp-server-http
- Expose via ngrok (for testing):
ngrok http 3000
- Add in ChatGPT: Settings → Connectors → Advanced → Developer Mode → Add your URL
Available Tools
getTolkCompilerVersion
Returns the current Tolk compiler version.
Example: "0.7.0"
runTolkCompiler
Compiles Tolk source code and returns the result.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
entrypointFileName |
string | Yes | Main .tolk file name |
sources |
Record<string, string> | Yes | Map of filename to source code |
optimizationLevel |
number (0-2) | No | Optimization level (default: 2) |
withStackComments |
boolean | No | Include stack comments in Fift output |
experimentalOptions |
string | No | Experimental compiler flags |
Success Response:
{
"status": "ok",
"fiftCode": "...",
"codeBoc64": "...",
"codeHashHex": "...",
"stderr": ""
}
Error Response:
{
"status": "error",
"message": "Error description"
}
Usage Examples
Ask Claude or ChatGPT:
Compile this Tolk contract:
fun onInternalMessage(myBalance: int, msgValue: int, msgFull: cell, msgBody: slice) {
// Simple contract
}
The AI will use the Tolk compiler to verify and compile your code.
Development
Build from Source
# Clone repository
git clone https://github.com/robustfengbin/tolk-mcp-server.git
cd tolk-mcp-server
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
Available Scripts
| Script | Description |
|---|---|
npm start |
Run stdio server (for Claude Desktop) |
npm run start:http |
Run HTTP server (for ChatGPT) |
npm run build |
Build TypeScript |
npm test |
Run tests |
npm run dev |
Build and run stdio server |
npm run dev:http |
Build and run HTTP server |
Project Structure
tolk-mcp-server/
├── src/
│ ├── index.ts # stdio transport server
│ └── server-http.ts # HTTP/SSE transport server
├── test/
│ └── test.ts # Test suite
├── docs/
│ ├── USAGE.md # English documentation
│ └── USAGE_CN.md # Chinese documentation
├── Dockerfile # Docker deployment
├── package.json
└── README.md
Deployment
Docker
# Build image
docker build -t tolk-mcp-server .
# Run container
docker run -p 3000:3000 tolk-mcp-server
Environment Variables
| Variable | Default | Description |
|---|---|---|
MCP_PORT |
3000 |
HTTP server port |
MCP_HOST |
0.0.0.0 |
HTTP server host |
API Endpoints (HTTP Server)
| Endpoint | Method | Description |
|---|---|---|
/mcp |
POST | MCP JSON-RPC endpoint |
/mcp |
GET | SSE stream for notifications |
/mcp |
DELETE | Session termination |
/health |
GET | Health check |
/ |
GET | Server info |
Requirements
- Node.js >= 18.0.0
Contributing
Contributions are welcome! Please read our Contributing Guide for details.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
References
- Tolk Language Documentation
- tolk-js Library
- Model Context Protocol
- ChatGPT MCP Support
- TON Society Grants & Bounties #1200
Acknowledgments
This project was created as part of the TON Society Grants & Bounties program.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。