MCP工具
95+ Model Context Protocol工具，实现与Claude的无缝集成
预构建的GitHub、Docker、浏览器自动化、数据库等集成。在几分钟内将Adverant Nexus连接到Claude Desktop或Claude Code。
什么是MCP？
Model Context Protocol (MCP) 是一种用于将AI模型连接到外部工具和数据源的开放标准。可以将其视为通用适配器，让Claude与您的应用程序、数据库和服务进行交互。
快速集成
几分钟内完成连接，而非数天
默认安全
内置认证和权限管理
可扩展
轻松构建自定义工具
工具分类
GitHub集成
30+工具完整的GitHub操作，包括仓库、Issue、Pull Request、代码审查和代码搜索。
精选工具：
create_repositoryfork_repositorycreate_pull_requestmerge_pull_requestcreate_issueupdate_issueadd_issue_commentcreate_branch+6更多
文件系统操作
15+工具读取、写入、编辑和管理文件和目录，具备高级搜索功能。
精选工具：
read_text_fileread_media_fileread_multiple_fileswrite_fileedit_filecreate_directorylist_directorydirectory_tree+3更多浏览器自动化
20+工具使用Playwright进行完整的浏览器控制，包括导航、交互和截图捕获。
精选工具：
browser_navigatebrowser_snapshotbrowser_clickbrowser_typebrowser_fill_formbrowser_screenshotbrowser_evaluatebrowser_wait_for+5更多Docker管理
10+工具使用Docker命令和Kubernetes操作进行容器和镜像管理。
精选工具：
docker_commandkubectl_commandget_k8s_podsget_k8s_servicesapply_k8s_manifestdelete_k8s_resourcerestart_serviceget_logs数据库工具
15+工具查询和管理PostgreSQL、Redis、Neo4j和Qdrant数据库。
精选工具：
query_databasebrain_store_memorybrain_recall_memorybrain_store_documentbrain_retrievebrain_store_entitybrain_query_entitiesbrain_get_entity+1更多网页抓取
5+工具使用Firecrawl进行高级网页抓取，实现内容提取和搜索。
精选工具：
firecrawl_scrapefirecrawl_searchfirecrawl_crawlfirecrawl_mapfirecrawl_extract安装
5分钟内启动和运行MCP工具
1启动Adverant Nexus
确保Adverant Nexus正在通过Docker Compose运行：
# Clone and start the platform
git clone https://github.com/adverant/nexus-platform.git
cd nexus-platform
docker-compose up -d
# Verify MCP server is running
curl http://localhost:9120/health2配置Claude Desktop
将MCP服务器添加到您的Claude Desktop配置：
# Edit Claude Desktop config
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"adverant-nexus": {
"url": "http://localhost:9120",
"name": "Adverant Nexus",
"description": "95+ tools for AI integration"
}
}
}更新配置后重新启动Claude Desktop。
3测试连接
验证Claude可以访问MCP工具：
试着问Claude：
"Adverant Nexus有哪些可用的MCP工具？"
配置示例
基础配置
{
"mcpServers": {
"adverant-nexus": {
"url": "http://localhost:9120",
"name": "Adverant Nexus",
"timeout": 30000,
"retries": 3
}
}
}生产配置
{
"mcpServers": {
"adverant-nexus": {
"url": "https://api.adverant.ai",
"name": "Adverant Nexus",
"apiKey": "your_api_key_here",
"timeout": 60000,
"retries": 3,
"ssl": {
"verify": true,
"cert": "/path/to/cert.pem"
}
}
}
}多服务器
{
"mcpServers": {
"adverant-nexus": {
"url": "http://localhost:9120",
"name": "Adverant Nexus"
},
"github": {
"url": "http://localhost:9121",
"name": "GitHub MCP Server"
},
"filesystem": {
"url": "http://localhost:9122",
"name": "Filesystem MCP Server"
}
}
}使用示例
GitHub操作
让Claude执行GitHub操作：
Example 1:
"Create a new issue in the adverant/nexus repo titled 'Add rate limiting' with the description 'We need to implement rate limiting on the API endpoints'"
Example 2:
"Search for all open pull requests in the adverant/nexus repo that mention 'authentication'"
Example 3:
"Create a new branch called 'feature/api-v2' from main in the adverant/nexus repo"
文件系统操作
处理文件和目录：
Example 1:
"Read the contents of /src/app/page.tsx and show me the component structure"
Example 2:
"Search for all TypeScript files in the /src directory that import React"
Example 3:
"Create a new directory at /src/components/cards if it doesn't exist"
记忆与知识图谱
存储和召回信息：
Example 1:
"Store this information: The API uses port 9100 for GraphRAG and port 9101 for MageAgent"
Example 2:
"What ports does the Adverant Nexus platform use?"
Example 3:
"Search my memories for information about Docker configuration"
服务器集成
将Adverant Nexus MCP工具集成到您自己的应用程序中
Node.js集成
import { MCPClient } from '@anthropic-ai/mcp-client';
// Connect to Adverant Nexus MCP server
const client = new MCPClient({
url: 'http://localhost:9120',
apiKey: process.env.NEXUS_API_KEY,
});
await client.connect();
// List available tools
const tools = await client.listTools();
console.log('Available tools:', tools.length);
// Execute a tool
const result = await client.executeTool({
name: 'brain_store_memory',
parameters: {
content: 'Important information about the project',
tags: ['project', 'documentation'],
},
});
console.log('Memory stored:', result);
// Disconnect
await client.disconnect();工具发现
以编程方式发现所有可用工具
列出所有工具
# HTTP request
GET http://localhost:9120/tools
# Response
{
"tools": [
{
"name": "brain_store_memory",
"description": "Store a memory with VoyageAI embeddings",
"parameters": {
"content": {
"type": "string",
"required": true,
"description": "Memory content to store"
},
"tags": {
"type": "array",
"required": false,
"description": "Tags for categorization"
}
}
},
// ... 94 more tools
]
}获取工具详情
# HTTP request
GET http://localhost:9120/tools/brain_store_memory
# Response
{
"name": "brain_store_memory",
"description": "Store a memory with VoyageAI embeddings for long-term recall",
"category": "Memory",
"parameters": {
"content": {
"type": "string",
"required": true,
"description": "Memory content to store"
},
"tags": {
"type": "array",
"items": { "type": "string" },
"required": false,
"description": "Tags for categorization"
},
"metadata": {
"type": "object",
"required": false,
"description": "Additional metadata"
}
},
"examples": [
{
"description": "Store a customer preference",
"parameters": {
"content": "Customer prefers email communication",
"tags": ["customer", "preference"]
}
}
]
}