Apollo.io MCP Server is a powerful implementation of the Model Context Protocol that connects AI assistants to Apollo.io data. It allows AI systems to enrich data for people and organizations, perform searches, find job postings, and execute Apollo.io operations through natural language commands without leaving the AI assistant interface.
To set up the Apollo.io MCP Server:
# Clone the repository
git clone https://github.com/lkm1developer/apollo-io-mcp-server.git
cd apollo-io-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
Before using the server, you need to obtain an Apollo.io API access token:
You can provide this token in either of two ways:
As an environment variable:
APOLLO_IO_API_KEY=your-api-key
As a command-line argument:
npm start -- --api-key=your-api-key
For development, create a .env
file in the project root:
APOLLO_IO_API_KEY=your-api-key
To start the MCP server:
# Start the server
npm start
# Or with a specific API key
npm start -- --api-key=your-api-key
# Run the SSE server with authentication
npx mcp-proxy-auth node dist/index.js
The server uses the mcp-proxy-auth package for authentication:
Set the authentication server URL:
export AUTH_SERVER_URL=https://your-auth-server.com/verify
The SSE URL will be available at:
localhost:8080/sse?apiKey=apikey
The authentication proxy:
The MCP server provides these tools for interacting with Apollo.io:
Enriches data for a single person.
Parameters:
first_name
(string, optional): Person's first namelast_name
(string, optional): Person's last nameemail
(string, optional): Person's email addressdomain
(string, optional): Company domainorganization_name
(string, optional): Organization nameExample:
{
"first_name": "John",
"last_name": "Doe",
"email": "[email protected]"
}
Enriches data for a single company.
Parameters:
domain
(string, optional): Company domainname
(string, optional): Company nameExample:
{
"domain": "apollo.io"
}
Finds people based on specified criteria.
Parameters:
q_organization_domains_list
(array, optional): List of organization domains to search withinperson_titles
(array, optional): List of job titles to search forperson_seniorities
(array, optional): List of seniority levels to search forExample:
{
"person_titles": ["Marketing Manager"],
"person_seniorities": ["vp"],
"q_organization_domains_list": ["apollo.io"]
}
Finds organizations based on specified criteria.
Parameters:
q_organization_domains_list
(array, optional): List of organization domains to search fororganization_locations
(array, optional): List of organization locations to search forExample:
{
"organization_locations": ["Japan", "Ireland"]
}
Finds job postings for a specific organization.
Parameters:
organization_id
(string, required): Apollo.io organization IDExample:
{
"organization_id": "5e60b6381c85b4008c83"
}
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.