Holochain MCP Server
Enables AI agents to search and retrieve Holochain documentation, including developer guides, HDK functions, and HDI API references.
README
Holochain MCP Server
A Model Context Protocol (MCP) server built with Effect TS that provides AI agents with access to Holochain documentation, including:
- Holochain Developer Documentation
- HDK (Holochain Development Kit) Rust Documentation
- HDI (Holochain Deterministic Integrity) Rust Documentation
Features
- Built with Effect TS: Leverages Effect's powerful type-safe error handling, concurrent operations, and functional programming patterns
- Search across all Holochain docs: Find relevant information across developer guides, HDK, and HDI documentation
- Fetch complete documentation pages: Get the full content of specific documentation pages
- HDK function lookup: Get detailed documentation for specific HDK functions
- Concept explanations: Access explanations of key Holochain concepts like source chain, DHT, links, etc.
- Module listing: Browse available HDK modules and their functions
- Robust error handling: Type-safe error management with Effect's error model
Available Tools
1. search_holochain_docs
Search across all Holochain documentation sources.
Parameters:
query(string, required): Search querysource(string, optional): Specific source to search ("all", "developer", "hdk", "hdi")
2. fetch_holochain_doc
Fetch the complete content of a specific documentation page.
Parameters:
url(string, required): URL of the documentation page
3. get_hdk_function
Get documentation for a specific HDK function.
Parameters:
functionName(string, required): Name of the HDK function (e.g., "create_entry", "get_links")
4. get_holochain_concept
Get documentation for Holochain concepts.
Parameters:
concept(string, required): Concept name (e.g., "source chain", "dht", "links")
5. list_hdk_modules
List available HDK modules and their main functions.
Parameters: None
Installation
- Clone this repository:
git clone https://github.com/soushi888/holochain-mcp
cd holochain-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
Usage
With Claude Desktop
Add the following to your Claude Desktop configuration file (~/claude_desktop_config.json):
{
"mcpServers": {
"holochain-docs": {
"command": "node",
"args": ["/absolute/path/to/holochain-mcp/build/index.js"]
}
}
}
With Claude Code CLI
claude mcp add-json holochain-docs '{
"command": "node",
"args": ["/absolute/path/to/holochain-mcp/build/index.js"],
"env": {}
}' -s user
With other MCP clients
Run the server directly:
npm start
Or use it as a module in your MCP-compatible application.
Development
Running in development mode
npm run dev
Testing with MCP Inspector
npm run inspector
Then open http://localhost:4000 in your browser to test the tools interactively.
Examples
Search for information about entries
Use the search_holochain_docs tool with query "create entry"
Get specific HDK function documentation
Use the get_hdk_function tool with functionName "create_entry"
Learn about Holochain concepts
Use the get_holochain_concept tool with concept "source chain"
Fetch a specific documentation page
Use the fetch_holochain_doc tool with url "https://developer.holochain.org/concepts/3_source_chain"
Architecture
The server is built using:
- Effect TS: Functional programming library with type-safe error handling and concurrency
- @effect/platform: Effect's platform abstractions for HTTP and other system operations
- @modelcontextprotocol/sdk: Official MCP TypeScript SDK
- cheerio: Server-side jQuery for parsing HTML content
- puppeteer: Browser automation for dynamic content fetching
- Effect Schema: Schema validation and parsing for tool inputs
- fuse.js: Fuzzy search functionality
Effect TS Benefits
This implementation showcases Effect TS features:
- Type-safe error handling: All errors are typed and handled explicitly
- Dependency injection: Services are properly layered and injected
- Concurrent operations: Multiple documentation sources are searched concurrently
- Functional composition: Clean, composable code using Effect's pipe and combinators
- Resource management: Automatic cleanup and resource management
Dual Fetching Strategy
The server uses two different approaches for fetching documentation:
- Puppeteer: Used for developer.holochain.org to handle dynamic content and JavaScript-rendered pages
- Standard HTTP: Used for docs.rs (HDK/HDI) static Rust documentation
The HolochainDocumentationService handles:
- Searching developer documentation by scraping common pages
- Searching Rust documentation (HDK/HDI) by checking module pages
- Fetching and parsing complete documentation pages
- Mapping function names and concepts to their documentation URLs
All operations are wrapped in Effect programs with proper error handling and resource management.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details.
Related Projects
- Effect MCP - MCP server for Effect documentation (inspiration for this project)
- Model Context Protocol - Official MCP repositories
- Holochain - The Holochain core repository
Support
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。