MCP

The Pinpoint Model Context Protocol (MCP) server enables AI-powered code editors like Cursor and Windsurf, plus general-purpose tools like Claude Desktop, to interact directly with your Pinpoint API documentation and execute API requests to get data from your Pinpoint account.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI applications to securely access external data sources and tools. The Pinpoint MCP server provides AI agents with:

Direct API access to Pinpoint functionality
Documentation search capabilities
Real-time data from your Pinpoint account
Code generation assistance for Pinpoint integrations

Pinpoint MCP Server Setup

Pinpoint hosts a remote MCP server at https://developers.pinpointhq.com/mcp. Configure your AI development tools to connect to this server.

Add to~/.cursor/mcp.json:

{
  "mcpServers": {
    "pinpoint": {
      "url": "https://developers.pinpointhq.com/mcp"
    }
  }
}

Executing requests

MCP server has execute-request tool, which your AI tool can use to do real API requests to your Pinpoint instance. To enable this, you need to add the API key and the host to the MCP configuration (passing headers):

❗️
We highly recommend creating a separate API key with read-only permission for usage with your AI tool.
MCP allows calling every API endpoint including those which create/update/remove data. Separate API key with read-only will ensure your AI tool won't cause any unintended data modifications/removal.

📘
Not all AI tools allow for passing headers to MCP calls. Some tools require paid accounts to do so.
E.g. ChatGPT dosn't support passing headers.

Add to~/.cursor/mcp.json:

{
  "mcpServers": {
    "pinpoint": {
      "url": "https://developers.pinpointhq.com/mcp",
      "headers": {
        "X-API-KEY": "<<YOUR-PINPOINT-API-KEY>>",
        "X-Original-Host": "<<YOUR-SUBDOMAIN>>.pinpointhq.com"
      }
    }
  }
}

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

Open your AI editor/CLI (Cursor, Windsurf, Claude etc.)
Start a new chat with the AI assistant
Ask about Pinpoint - try questions like:
- "How do I create a new application?"
- "Show me an example of custom fields creation"
- "Create an assessment integration using Pinpoint"
- "Prepare a report from the last 50 candidates"
- "Which countries do we get most applications from?"

The AI should now have access to your Pinpoint account data and documentation through the MCP server.

List of tools

Tool	What it does
`list-specs`	Lists all API specs available in the project, with their titles
`list-endpoints`	Returns all API paths and HTTP methods with their summaries
`get-endpoint`	Returns full details on a specific endpoint: description, parameters, security
`get-request-body`	Returns the request body schema for an endpoint
`get-response-schema`	Returns the response schema for a specific endpoint and status code
`list-security-schemes`	Lists all authentication methods defined in your API spec
`search-specs`	Case-insensitive search across all paths, operations, and schemas
`execute-request`	Makes a live API call and returns the response. Requires auth headers to be forwarded (see Executing requests section above)
`get-code-snippet`	Generates a working code snippet for any endpoint in any programming language