querypie

Deprecated — Replaced by the MCP Server built into QueryPie ACP 11.5.0. Please use the in‑product server for the latest features and security.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio querypie-querypie-mcp-server docker run -i querypie-mcp-server:latest \
  --env QP_MCP_PORT="Set the port QueryPie MCP should listen on (default 8080)" \
  --env QP_MCP_DEBUG="Enable debug logging (true/false)"

How to use

This MCP server repository previously provided an MCP server to help LLMs and AI agents administer QueryPie ACP. As of the December 2025 release, the MCP Server functionality is built into QueryPie ACP 11.5.0, and the standalone MCP server in this repository is no longer maintained or recommended for use. If you are experimenting locally, you can deploy the legacy server image described here to understand how MCP interactions were structured (commands, events, and responses) and to review the configuration patterns. In practice, you should rely on the MCP Server embedded in QueryPie ACP for production use. The tools and capabilities demonstrated by this repository aligned with configuring AI coding assistants to perform tasks under ACP access controls, using LLMs to safely execute operations.

How to install

Prerequisites:

Docker installed on your host machine
Basic familiarity with running containers

Installation steps:

Pull the MCP server image (legacy): docker pull querypie-mcp-server:latest
Run the MCP server container (as a background or interactive session): docker run -d --name querypie-mcp-server -p 8080:8080 -e QP_MCP_PORT=8080 -e QP_MCP_DEBUG=true querypie-mcp-server:latest
Confirm the server is up: curl http://localhost:8080/health
Configure your MCP client to point at the server endpoint, e.g. http://localhost:8080

Note: Because this repository’s MCP Server has been superseded by the built-in MCP Server in QueryPie ACP 11.5.0, consider migrating to the product’s MCP server for ongoing updates and security improvements.

Additional notes

Tips and considerations:

This repository is deprecated; use the MCP Server built into QueryPie ACP 11.5.0 for production deployments.
If you still deploy the legacy container, ensure network access between your AI agent and the MCP server, and configure environment variables as needed (QP_MCP_PORT, QP_MCP_DEBUG).
Check for compatibility with your ACP version and the MCP configuration guide referenced in the legacy docs.
Typical MCP usage involves defining prompts, allowed actions, and access controls so that LLMs can perform administrative tasks safely within ACP.
If you encounter connectivity or authentication issues, verify that the container port is accessible and that any required API keys or tokens are correctly provided to the client.

Related MCP Servers

trpc-agent-go

949

trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.

station

385

Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

tiger-cli

Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.

gopls

MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.

kubernetes

A Model Context Protocol (MCP) server for the Kubernetes API.

gcp-cost

💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go