Node.js-based Model Context Protocol server providing seamless access to LinkedIn profiles, company data, and advanced employee search capabilities via Proxycurl's API for MCP-compatible clients.
Unlock the full potential of Proxycurl MCP Server through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
Discover shared experiences
This is a Node.js-based Model Context Protocol (MCP) server that exposes Proxycurl's LinkedIn data API. It can be used with any MCP-compatible client (e.g., Claude Desktop) to access LinkedIn profile data, company information, and search for employees.
Clone this repository:
git clone https://github.com/dbogardus/proxycurl-mcp-server.git cd proxycurl-mcp-server
Install dependencies:
npm install
Install the MCP server globally:
npm install -g .
There are two ways to configure your Proxycurl API key:
Set the PROXYCURL_API_KEY
environment variable:
export PROXYCURL_API_KEY=your_api_key_here
This is useful for development or when running the CLI directly.
To configure Claude Desktop to use this MCP server:
Open Claude Desktop
Click the settings (⚙️) icon in the top right
Select the "Model Context Protocol" tab
Click "Add MCP Configuration"
Enter the following information:
Proxycurl LinkedIn API
npx
["proxycurl-mcp", "--api-key", "YOUR_ACTUAL_API_KEY"]
Example configuration in claude_desktop_config.json:
{ "mcpServers": [ { "name": "Proxycurl LinkedIn API", "command": "npx", "args": ["proxycurl-mcp", "--api-key", "YOUR_ACTUAL_API_KEY"] } ] }
Replace YOUR_ACTUAL_API_KEY
with your Proxycurl API key (get one at https://nubela.co/proxycurl/)
Click "Save"
Restart Claude Desktop to apply changes
Once configured, your MCP client will be able to access LinkedIn data through the following tools:
get_person_profile
: Get a person's LinkedIn profile by URL
linkedinUrl: "https://www.linkedin.com/in/williamhgates"
get_company_profile
: Get a company's LinkedIn profile by URL
linkedinUrl: "https://www.linkedin.com/company/microsoft"
lookup_person
: Find a person's LinkedIn profile by name and company
name: "Bill Gates", company: "microsoft.com"
search_employees
: Search for employees at a company with role and keyword filters
linkedinUrl: "https://www.linkedin.com/company/microsoft", role: "Software Engineer"
search_companies
: Search for companies by name or domain
query: "Microsoft"
or query: "microsoft.com", limit: 5
search_people
: Search for people on LinkedIn by keywords, title, company, and location
query: "data science", title: "Lead", companyDomain: "microsoft.com", location: "Seattle"
advanced_search_companies
: Advanced search for companies with detailed filtering options
country: "US", industry: "technology", employee_count_min: 1000, founded_after_year: 2010
To modify the server or add new features:
server.js
to add or modify API endpointsnpm install -g .
to install your changes globallytest.env
)For local development and running test scripts (e.g., those in the tests/
directory) directly, you can use a test.env
file in the project root to manage your API key and debug settings. This file is typically included in .gitignore
and should not be committed to the repository.
Create a test.env
file with the following content:
PROXYCURL_API_KEY=your_actual_proxycurl_api_key_here
Replace your_actual_proxycurl_api_key_here
with your Proxycurl API key. The test scripts are often configured to load environment variables from this file if it exists.
MIT
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!