Dokploy/mcp

What it solves

Dokploy MCP Server allows AI models and MCP-compatible clients (like Cursor, VS Code, and Claude Desktop) to programmatically interact with a Dokploy server. It bridges the gap between an LLM's reasoning and the actual management of your infrastructure, enabling AI to manage projects, applications, and databases via the Dokploy API.

How it works

The server implements the Model Context Protocol (MCP), exposing 508 different tools across 49 categories that map directly to Dokploy API endpoints. It can be deployed via npx, Docker, or as a standalone HTTP server. To prevent LLM context window issues or performance degradation, it includes a filtering system using presets (e.g., minimal, core, deploy) or specific tags to limit which tools are exposed to the AI.

Who it’s for

Developers and DevOps engineers using Dokploy for server management who want to automate infrastructure tasks or manage their deployments using AI-powered IDEs and chat interfaces.

Highlights

• Comprehensive API Coverage: Provides 508 tools covering everything from application lifecycles and Docker Compose to database management and SSO.
• Flexible Transport: Supports both Stdio (for desktop apps) and HTTP (Streamable HTTP and legacy SSE) modes.
• Granular Tool Filtering: Allows users to load only specific toolsets via presets or tags to optimize LLM performance.
• Security-First: Includes a built-in redaction system (DOKPLOY_REDACT_ENV) to prevent sensitive secrets from being sent to the LLM context.
• Broad Client Support: Ready-to-use configurations for Cursor, VS Code, Windsurf, Claude Code, Zed, and BoltAI.