A Model Context Protocol (MCP) server that provides comprehensive access to LinkedIn data and functionalities using the HorizonDataWave API, enabling not only data retrieval but also robust management of user accounts.
What is hdw-mcp-server
HDW MCP Server
A Model Context Protocol (MCP) server that provides comprehensive access to LinkedIn data and functionalities using the HorizonDataWave API, enabling not only data retrieval but also robust management of user accounts.
Features
-
LinkedIn Users Search: Filter and search for LinkedIn users by keywords, name, title, company, location, industry, and education.
-
Profile Lookup: Retrieve detailed profile information for a LinkedIn user.
-
Email Lookup: Find LinkedIn user details by email address.
-
Posts & Reactions: Retrieve a user's posts and associated reactions.
-
Post Reposts & Comments: Retrieve reposts and comments for a specific LinkedIn post.
-
Account Management:
- Chat Functionality: Retrieve and send chat messages via the LinkedIn management API.
- Connection Management: Send connection invitations to LinkedIn users.
- Post Commenting: Create comments on LinkedIn posts or replies.
- User Connections: Retrieve a list of a user's LinkedIn connections.
-
Company Search & Details:
- Google Company Search: Find LinkedIn companies using Google search – the first result is typically the best match.
- Company Lookup: Retrieve detailed information about a LinkedIn company.
- Company Employees: Retrieve employees for a given LinkedIn company.
-
Google Search
Tools
HDW MCP Server exposes several tools through the MCP protocol. Each tool is defined with its name, description, and input parameters:
-
Search LinkedIn Users
Name:search_linkedin_users
Description: Search for LinkedIn users with various filters.
Parameters:keywords
(optional): Any keyword for search.first_name
,last_name
,title
,company_keywords
,school_keywords
(optional).current_company
,past_company
,location
,industry
,education
(optional).count
(optional, default: 10): Maximum number of results (max 1000).timeout
(optional, default: 300): Timeout in seconds (20–1500).
-
Get LinkedIn Profile
Name:get_linkedin_profile
Description: Retrieve detailed profile information about a LinkedIn user.
Parameters:user
(required): User alias, URL, or URN.with_experience
,with_education
,with_skills
(optional, default: true).
-
Get LinkedIn Email User
Name:get_linkedin_email_user
Description: Look up LinkedIn user details by email.
Parameters:email
(required): Email address.count
(optional, default: 5).timeout
(optional, default: 300).
-
Get LinkedIn User Posts
Name:get_linkedin_user_posts
Description: Retrieve posts for a LinkedIn user by URN.
Parameters:urn
(required): User URN (must include prefix, e.g.fsd_profile:...
).count
(optional, default: 10).timeout
(optional, default: 300).
-
Get LinkedIn User Reactions
Name:get_linkedin_user_reactions
Description: Retrieve reactions for a LinkedIn user by URN.
Parameters:urn
(required).count
(optional, default: 10).timeout
(optional, default: 300).
-
Get LinkedIn Chat Messages
Name:get_linkedin_chat_messages
Description: Retrieve top chat messages from the LinkedIn management API.
Parameters:user
(required): User URN (with prefix).count
(optional, default: 20).timeout
(optional, default: 300).
-
Send LinkedIn Chat Message
Name:send_linkedin_chat_message
Description: Send a chat message using the LinkedIn management API.
Parameters:user
(required): Recipient user URN (with prefix).text
(required): Message text.timeout
(optional, default: 300).
-
Send LinkedIn Connection Request
Name:send_linkedin_connection
Description: Send a connection invitation to a LinkedIn user.
Parameters:user
(required).timeout
(optional, default: 300).
-
Send LinkedIn Post Comment
Name:send_linkedin_post_comment
Description: Create a comment on a LinkedIn post or reply.
Parameters:text
(required): Comment text.urn
(required): Activity or comment URN.timeout
(optional, default: 300).
-
Get LinkedIn User Connections
Name:get_linkedin_user_connections
Description: Retrieve a list of LinkedIn user connections.
Parameters:connected_after
(optional): Timestamp filter.count
(optional, default: 20).timeout
(optional, default: 300).
-
Get LinkedIn Post Reposts
Name:get_linkedin_post_reposts
Description: Retrieve reposts for a LinkedIn post.
Parameters:urn
(required): Post URN (must start withactivity:
).count
(optional, default: 10).timeout
(optional, default: 300).
-
Get LinkedIn Post Comments
Name:get_linkedin_post_comments
Description: Retrieve comments for a LinkedIn post.
Parameters:urn
(required).sort
(optional, default:"relevance"
; allowed values:"relevance"
,"recent"
).count
(optional, default: 10).timeout
(optional, default: 300).
-
Get LinkedIn Google Company
Name:get_linkedin_google_company
Description: Search for LinkedIn companies via Google – the first result is typically the best match.
Parameters:keywords
(required): Array of company keywords.with_urn
(optional, default: false).count_per_keyword
(optional, default: 1; range 1–10).timeout
(optional, default: 300).
-
Get LinkedIn Company
Name:get_linkedin_company
Description: Retrieve detailed information about a LinkedIn company.
Parameters:company
(required): Company alias, URL, or URN.timeout
(optional, default: 300).
-
Get LinkedIn Company Employees
Name:get_linkedin_company_employees
Description: Retrieve employees of a LinkedIn company.
Parameters:companies
(required): Array of company URNs.keywords
,first_name
,last_name
(optional).count
(optional, default: 10).timeout
(optional, default: 300).
Setup Guide
Installing via Smithery
To install HDW MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @horizondatawave/hdw-mcp-server --client claude
1. Clone the Repository (macOS)
Open your terminal and run the following commands:
# Clone the repository
git clone https://github.com/horizondatawave/hdw-mcp-server.git
# Change directory to the project folder
cd hdw-mcp-server
# Install dependencies
npm install
2. Obtain Your API Credentials
Register at app.horizondatawave.ai to get your API key and 100 free credits. You will receive your HDW_ACCESS_TOKEN and HDW_ACCOUNT_ID.
3. Configure the Environment
Create a .env
file in the root of your project with the following content:
HDW_ACCESS_TOKEN=YOUR_HD_W_ACCESS_TOKEN
HDW_ACCOUNT_ID=YOUR_HD_W_ACCOUNT_ID
4. Client Configuration
4.1 Claude Desktop
Update your Claude configuration file (claude_desktop_config.json
) with the following content:
{
"mcpServers": {
"hdw": {
"command": "npx",
"args": ["-y","@horizondatawave/mcp"],
"env": {
"HDW_ACCESS_TOKEN": "YOUR_HD_W_ACCESS_TOKEN",
"HDW_ACCOUNT_ID": "YOUR_HD_W_ACCOUNT_ID"
}
}
}
}
Configuration file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
4.2 Cursor
Easy way:
Open Cursor Settings and add a new MCP server with the command:
env HDW_ACCESS_TOKEN=your-access-token HDW_ACCOUNT_ID=your-account-id node /path/to/your/build/index.js
Safe way:
Copy the provided template run.template.sh
to a new file (e.g. run.sh
), update it with your credentials, and configure Cursor to run:
sh /path/to/your/run.sh
4.3 Windsurf
Update your Windsurf configuration file (mcp_config.json
) with the following content:
{
"mcpServers": {
"hdw": {
"command": "node",
"args": ["/path/to/your/build/index.js"],
"env": {
"HDW_ACCESS_TOKEN": "YOUR_HD_W_ACCESS_TOKEN",
"HDW_ACCOUNT_ID": "YOUR_HD_W_ACCOUNT_ID"
}
}
}
}
Note: After configuration, you can disable official web tools to conserve your API credits.
MCP Client Example Configuration
Below is an example configuration for an MCP client (e.g., a custom integration):
{
"mcpServers": {
"hdw": {
"command": "npx",
"args": ["-y","@horizondatawave/mcp"],
"env": {
"HDW_ACCESS_TOKEN": "YOUR_HD_W_ACCESS_TOKEN",
"HDW_ACCOUNT_ID": "YOUR_HD_W_ACCOUNT_ID"
}
}
}
}
Replace the paths and credentials with your own values.
License
This project is licensed under the MIT License.
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
Brave Search MCP
Integrate Brave Search capabilities into Claude through MCP. Enables real-time web searches with privacy-focused results and comprehensive web coverage.
zhixiaoqiang antd components mcp
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
yeonupark mcp soccer data
An MCP server that provides real-time football data based on the SoccerDataAPI.
webflow mcp server
Model Context Protocol (MCP) server for the Webflow Data API.
uday210 salesforce mcp server
Model Context Protocol server for Salesforce REST API integration
SecretiveShell mcp windows
MCP server for the windows API.
RmMargt searchAPI mcp
SearchAPI MCP for Google searches
r huijts strava mcp
A Model Context Protocol (MCP) server that connects to Strava API, providing tools to access Strava data through LLMs
OpenLinkSoftware mcp pyodbc server
A simple MCP ODBC server using FastAPI, ODBC and PyODBC.
junjiem dify plugin mcp compat dify tools
Dify 1.0 Plugin Convert your Dify tools's API to MCP compatible API
Submit Your MCP Server
Share your MCP server with the community
Submit Now