solid-mcp

solid-mcp

MCP server for the Solid protocol enabling AI models to read, write, search, and manage resources in Solid pods.

Category
访问服务器

README

solid-mcp

GitHub license npm version build Dependabot semantic-release

⚠️ WARNING: This entire project was created by generative AI and has not been reviewed or tested by a human yet. Use with caution in production environments.

Anthropic Model Context Protocol (MCP) integration for the Solid protocol.

This library enables AI models like Claude to access and manipulate data stored in Solid pods through the Model Context Protocol. It allows AI systems to read, write, search, and manage resources in Solid pods while respecting user privacy and control over their data.

Features

  • 🔄 Seamless integration between Anthropic's MCP and Solid pods
  • 📁 Read and write resources in Solid pods
  • 🔍 Search for resources and contents
  • 📂 Create and manage containers
  • 🔐 Authentication support for secure pod access
  • 🧰 Tool-based API for integration with AI models
  • 📊 Structured data handling

Installation

npm install @jeswr/solid-mcp

Usage

Basic Setup

import { createSolidMCPServer, SolidPodConfig } from '@jeswr/solid-mcp';

// Configure access to a Solid Pod
const config: SolidPodConfig = {
  podUrl: 'https://example.solidcommunity.net/',
  auth: {
    type: 'bearer',
    token: 'your-solid-access-token',
  }
};

// Create the MCP server
const server = createSolidMCPServer(config);

Reading a Resource

// Example MCP request to read a resource
const request = {
  action: 'read_resource',
  parameters: {
    uri: '/profile/card',
    include_content: true,
  },
};

// Handle the request
const response = await server.handleRequest(request);
console.log('Response:', response);

Writing a Resource

// Example MCP request to write a resource
const request = {
  action: 'write_resource',
  parameters: {
    uri: '/examples/hello.txt',
    content: 'Hello, Solid World!',
    content_type: 'text/plain',
  },
};

// Handle the request
const response = await server.handleRequest(request);
console.log('Response:', response);

Listing Container Contents

// Example MCP request to list a container
const request = {
  action: 'list_container',
  parameters: {
    uri: '/examples/',
  },
};

// Handle the request
const response = await server.handleRequest(request);
console.log('Response:', response);

Searching for Resources

// Example MCP request to search for resources
const request = {
  action: 'search',
  parameters: {
    container_uri: '/',
    search_term: 'profile',
    recursive: true,
  },
};

// Handle the request
const response = await server.handleRequest(request);
console.log('Response:', response);

API Reference

createSolidMCPServer(config: SolidPodConfig): SolidMCPServer

Creates a new MCP server for a Solid Pod.

SolidClient

Client for interacting with a Solid Pod.

  • readResource(uri: string, includeContent?: boolean): Promise<SolidResourceResponse>
  • writeResource(uri: string, content: any, contentType: string): Promise<SolidResourceResponse>
  • deleteResource(uri: string): Promise<boolean>
  • createContainer(uri: string): Promise<SolidResourceResponse>

SolidMCPServer

MCP server for Solid Pod integration.

  • handleRequest(request: any): Promise<any>
  • getService(): SolidMCPService

Integration with Anthropic Claude

This library makes it easy to integrate Solid pods with Anthropic's Claude AI through the Model Context Protocol. Claude can access and manipulate data in Solid pods while respecting user privacy and control.

Example Claude Integration

// In your Claude MCP client implementation
const solidMCPServer = createSolidMCPServer({
  podUrl: 'https://example.solidcommunity.net/',
  auth: { type: 'bearer', token: 'your-solid-access-token' }
});

// When Claude needs to access data
const claudeRequest = {
  action: 'read_resource',
  parameters: { uri: '/notes/important.txt' }
};

const response = await solidMCPServer.handleRequest(claudeRequest);
// Provide the response to Claude for context

Running Examples

The library includes example code showing how to use the various features:

npm run example

License

©2025–present Jesse Wright, MIT License.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选