PI API MCP Server

@mingzilla

Basic information

About PI API MCP Server

MCP (Model Context Protocol) Server for the PI API

PI API MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "pi-api-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@mingzilla/pi-api-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

PI API MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is PI API MCP Server?

A Model Context Protocol (MCP) server that provides standardized tools and resources for interacting with the PI Dashboard API. It enables Claude and other MCP-compatible AI assistants to securely access and manage PI Dashboard resources, including categories and charts.

How to use PI API MCP Server?

Install via Smithery, Docker, npm, or local build. Configure the MCP client (e.g., Claude for Desktop) with the provided JSON configuration, specifying the API URL and optional auth token. Use the available tools and prompts to authenticate, list/analyze categories and charts, and export chart data.

Key features of PI API MCP Server

Authenticate and manage sessions with the PI Dashboard API
List, get, create, update, and delete categories
List, get, delete, and export charts in various formats
Filter entities using filterable attributes
Analyze categories and charts with built-in prompts
Session management tools for token refresh and logout

Use cases of PI API MCP Server

Authenticate to the PI Dashboard API and check connection status
List and analyze all categories in the dashboard
Retrieve and analyze charts, including metadata and JSON data extraction
Export specific charts as PDF or other formats
Compare data between two charts using analysis prompts

Frequently asked questions

What runtime dependencies does PI API MCP Server require?

Node.js is required for npm/npx installation. Docker is recommended for containerized setups.

How do I configure the API URL?

You can set the API URL via the `--api-url` command-line argument at initialization, or use the `set-api-url` tool after starting the server.

What authentication methods are supported?

The server supports token-based authentication (using `keep-session-alive`) and username/password authentication (via `authenticate-with-credentials` as a last resort).

Can I filter charts and categories?

Yes. Use the `get-filterable-attributes` tool to discover available filters, then apply them when listing charts or categories.

Where does my data live?

The server acts as a proxy to your PI Dashboard API instance. No data is stored by the server itself—all data stays on the PI Dashboard backend.

Comments

More Developer Tools MCP servers

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

MilliGate (x402 Crypto Paywall)

MilliGate Core

MilliGate is a developer-first remote MCP server that functions as a secure crypto paywall. By leveraging the HTTP 402 (Payment Required) protocol, it allows developers to monetize AI agents, APIs, and digital infrastruc