Mcp Explorium

ai.explorium由 explorium.ai 发布官方发布者v1.0.1更新于 Oct 25, 2026

Access live company and contact data from Explorium's AgentSource B2B platform.

已验证Streamable HTTP可网页运行网页搜索与抓取商业与电商

概览

AI 生成的概览

Explorium 的远程 MCP 服务器让助手获取实时 B2B 公司与联系人数据,用于搜索、信息补全和商业事件研究。

可以做什么
按名称、域名或企业 ID 匹配和查询公司,补全企业画像与技术栈信息,并追踪融资、办公地点变动、招聘趋势等商业事件。发现公司内的专业人士与联系人,补全联系方式、工作经历和职业档案,并追踪职位变动与职业里程碑。将数十个外部数据源的结果带入助手工作流,用于线索调研、潜在客户筛选和外联撰写。
适用场景
适合销售、招聘或合作调研场景,让助手无需离开对话即可查找公司、确定合适联系人并收集企业画像或职业信息。也适合回答某公司的业务挑战、技术栈或近期动态等问题。
运行要求
通过 Streamable HTTP 访问的远程 MCP 端点(文档也提供 SSE 和本地 npx mcp-remote 桥接方式)。清单声明需要 OAuth 认证。README 说明远程连接无需 API 密钥,而 Docker 自托管需要 API_ACCESS_TOKEN 环境变量。需要能访问 Explorium 托管服务器的网络。
安装前请注意
该服务器会返回邮箱、电话、工作经历等个人联系数据,应按适用的隐私法规处理。远程连接通过 OAuth 认证;Docker 方式需要 API_ACCESS_TOKEN 密钥,应避免写入共享配置。README 指出仓库中的服务器文件只是占位符,真正的服务器由 Explorium 托管。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Explorium,将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/ai.explorium%2Fmcp-explorium/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "explorium": {
      "type": "http",
      "url": "https://mcp-github-registry.explorium.ai/mcp"
    }
  }
}

README

Explorium Business Data Hub

[MIT License] [Node.js Version] [MCP Compatible] [Claude Ready] [OpenAI Compatible] [TypeScript]

[Explorium Logo]

Discover companies, contacts, and business insights—powered by dozens of trusted external data sources.

This repository contains the configuration and setup files for connecting to Explorium's Model Context Protocol (MCP) server, enabling AI tools to access comprehensive business intelligence data.

Overview

The Explorium Business Data Hub provides AI tools with access to:

  • Company Search & Enrichment: Find companies by name, domain, or attributes with detailed firmographics
  • Contact Discovery: Locate and enrich professional contact information
  • Business Intelligence: Access technology stack, funding history, growth signals, and business events
  • Real-Time Data: Up-to-date information from dozens of trusted external data sources
  • Workflow Integration: Seamlessly integrate business data into AI-powered workflows

Search any company or professional for everything from emails and phone numbers to roles, growth signals, tech stack, business events, website changes, and more. Find qualified leads, research prospects, identify talent, or craft personalized outreach—all without leaving your AI tool.

Examples

Example 1: Partnership Opportunity Research

Who should I contact for partnership with monday.com? Get anyone who can promote a partnership with them. Bring me all the contact details you can find

Example 2: Business Challenge Analysis

What are the business challenges of amazon?

Example 3: Leadership Team Discovery

Get the engineering leadership team at Palo Alto Networks

Installation

Install in Claude Desktop
Remote Server Connection

Open Claude Desktop and navigate to Settings > Connectors > Add Custom Connector. Enter the name as Explorium and the remote MCP server URL as https://mcp.explorium.ai/mcp.

Local Server Connection

Open Claude Desktop developer settings and edit your claude_desktop_config.json file to add the following configuration. See Claude Desktop MCP docs for more info.

json
{  "mcpServers": {    "explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}
Install in Cursor

Go to: Settings -> Cursor Settings -> MCP -> Add new global MCP server

Pasting the following configuration into your Cursor ~/.cursor/mcp.json file is the recommended approach. You may also install in a specific project by creating .cursor/mcp.json in your project folder. See Cursor MCP docs for more info.

Cursor Remote Server Connection
json
{  "mcpServers": {    "explorium": {      "url": "https://mcp.explorium.ai/mcp"    }  }}
Cursor Local Server Connection
json
{  "mcpServers": {    "explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}
Install in Windsurf

Add this to your Windsurf MCP config file. See Windsurf MCP docs for more info.

Windsurf Remote Server Connection
json
{  "mcpServers": {    "explorium": {      "serverUrl": "https://mcp.explorium.ai/mcp"    }  }}
Windsurf Local Server Connection
json
{  "mcpServers": {    "explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}
Install in VS Code

Add this to your VS Code MCP config file. See VS Code MCP docs for more info.

VS Code Remote Server Connection
json
"mcp": {  "servers": {    "explorium": {      "type": "http",      "url": "https://mcp.explorium.ai/mcp"    }  }}
VS Code Local Server Connection
json
"mcp": {  "servers": {    "explorium": {      "type": "stdio",      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}
Install in Zed

It can be installed via Zed Extensions or you can add this to your Zed settings.json. See Zed Context Server docs for more info.

json
{  "context_servers": {    "Explorium": {      "command": {        "path": "npx",        "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]      },      "settings": {}    }  }}
Install in Cline

You can easily install Explorium through the Cline MCP Server Marketplace by following these instructions:

  1. Open Cline.
  2. Click the hamburger menu icon (☰) to enter the MCP Servers section.
  3. Use the search bar within the Marketplace tab to find Explorium.
  4. Click the Install button.
Install in Roo Code

Add this to your Roo Code MCP configuration file. See Roo Code MCP docs for more info.

Roo Code Remote Server Connection
json
{  "mcpServers": {    "explorium": {      "type": "streamable-http",      "url": "https://mcp.explorium.ai/mcp"    }  }}
Roo Code Local Server Connection
json
{  "mcpServers": {    "explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}
Install in JetBrains AI Assistant

See JetBrains AI Assistant Documentation for more details.

  1. In JetBrains IDEs go to Settings -> Tools -> AI Assistant -> Model Context Protocol (MCP)
  2. Click + Add.
  3. Click on Command in the top-left corner of the dialog and select the As JSON option from the list
  4. Add this configuration and click OK
json
{  "mcpServers": {    "explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}
  1. Click Apply to save changes.
  2. The same way explorium could be added for JetBrains Junie in Settings -> Tools -> Junie -> MCP Settings
Install in Kiro

See Kiro Model Context Protocol Documentation for details.

  1. Navigate Kiro > MCP Servers
  2. Add a new MCP server by clicking the + Add button.
  3. Paste the configuration given below:
json
{  "mcpServers": {    "Explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"],      "env": {},      "disabled": false,      "autoApprove": []    }  }}
  1. Click Save to apply the changes.

Connecting to Explorium MCP

For advanced users or other MCP clients, you can connect using these methods:

You can connect your AI tool to Explorium using the Model Context Protocol (MCP) through several methods:

Streamable HTTP (Recommended)

  • URL: https://mcp.explorium.ai/mcp
  • JSON config:
json
{  "mcpServers": {    "Explorium": {      "url": "https://mcp.explorium.ai/mcp"    }  }}

SSE (Server-Sent Events)

  • URL: https://mcp.explorium.ai/sse
  • JSON config:
json
{  "mcpServers": {    "Explorium": {      "url": "https://mcp.explorium.ai/sse"    }  }}

STDIO (Local Server)

  • JSON config:
json
{  "mcpServers": {    "explorium": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://mcp.explorium.ai/mcp"]    }  }}

API Key Requirements

Important: Different connection methods have different authentication requirements:

  • ✅ Claude Desktop Extension - No API key required
  • ✅ MCP Remote Connections (Streamable HTTP/SSE/STDIO) - No API key required
  • 🔑 Docker Self-Hosting - Requires API key

Getting Your API Key

For Docker deployment, you'll need an API access token. Get yours at: https://admin.explorium.ai/api-key

Docker Deployment

This repository includes Docker configuration for self-hosting:

bash
# Build the Docker imagedocker build -t explorium-mcp .
# Run the container with API access tokendocker run -e API_ACCESS_TOKEN=your_explorium_access_token explorium-mcp

Required Environment Variables:

  • API_ACCESS_TOKEN - Your Explorium API access token for authentication (get it here)

You can also use a .env file or docker-compose for easier management:

yaml
# docker-compose.ymlversion: '3.8'services:  explorium-mcp:    build: .    ports:      - "44280:44280"    environment:      - API_ACCESS_TOKEN=${API_ACCESS_TOKEN}

Available Tools

Once connected, your AI tool will have access to tools for:

  • Business Matching: Find companies by name, domain, or business ID
  • Business Enrichment: Get detailed firmographics, technographics, and business intelligence
  • Business Events: Track funding rounds, office changes, hiring trends, and company developments
  • Prospect Discovery: Search for professionals and contacts within companies
  • Prospect Enrichment: Access contact information, work history, and professional profiles
  • Prospect Events: Track role changes, company moves, and career milestones

Troubleshooting Connection Issues

If you're experiencing issues connecting your AI tool to Explorium MCP:

  1. Check MCP Client Support Verify that your AI tool supports MCP clients and can connect to MCP servers. Not all AI tools have this capability built-in yet.

  2. Verify Remote Server Support Some AI tools have MCP clients but don't support remote connections. If this is the case, you may still be able to connect using our Docker configuration or local server setup.

  3. Request MCP Support If your AI tool doesn't support MCP at all, we recommend reaching out to the tool's developers to request MCP server connection support.

Configuration Files

This repository contains:

  • package.json - Node.js dependencies and scripts
  • manifest.json - Extension metadata and configuration
  • Dockerfile - Container configuration for self-hosting
  • server/index.js - Placeholder file (does not contain actual MCP implementation)
  • entrypoint.sh - Docker container entry point

Important Note: The server/index.js file in this repository is just a placeholder and does not contain the actual MCP server implementation. To use Explorium MCP, you need to connect to the remote server at https://mcp.explorium.ai/mcp using mcp-remote or through the connection methods described above. The actual MCP server is hosted by Explorium and accessible via the remote URLs.

Documentation & Support

For technical support, contact [email protected].

License

This project is licensed under the MIT License. See LICENSE for details.


来源:README.md,提交 7aafdff

工具

0
该服务器需要 API 密钥等凭据,因此 SourceWeft 无法在没有凭据的情况下读取其工具,也未收录。

版本历史

1
  1. v1.0.1最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Explorium 集成