PI API MCP Server

MCP (Model Context Protocol) Server for the PI API

Catalog onlyCatalog onlySTDIO

Overview

PI API MCP Server is a Model Context Protocol (MCP) server that provides standardized tools and resources for interacting with the PI Dashboard API, enabling AI assistants to securely access and manage PI Dashboard resources.

To use the PI API MCP Server, ensure it is running, set the API URL, authenticate with your credentials, and then you can list charts and analyze data.

Standardized tools for API interaction - Secure access to PI Dashboard resources - Support for chart analysis and metadata retrieval - Docker installation for easy setup

Integrating AI assistants with the PI Dashboard API.
Analyzing and retrieving data from charts.
Managing categories and charts within the PI Dashboard.

Add to your AI client

Use these steps to connect PI API MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "pi-api-mcp-server-mingzilla": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pi-api-mcp-server-mingzilla"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "pi-api-mcp-server-mingzilla": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pi-api-mcp-server-mingzilla"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "pi-api-mcp-server-mingzilla": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pi-api-mcp-server-mingzilla"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "pi-api-mcp-server-mingzilla": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pi-api-mcp-server-mingzilla"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pi-api-mcp-server-mingzilla": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pi-api-mcp-server-mingzilla"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "pi-api-mcp-server-mingzilla": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-pi-api-mcp-server-mingzilla"
      ]
    }
  }
}

FAQ

What is the purpose of the PI API MCP Server?

It provides a standardized way for AI assistants to interact with the PI Dashboard API.

How do I install the server?

You can install it using Docker or via NPM for local execution.

Can I use it without Docker?

Yes, you can run it locally using Node.js.

Research and data