Tpl. MCP Server

MCP Server for Directus with Schema Management

Remote serverstreamable-httpTypeScript

What is the Tpl. MCP server?

If you want an AI assistant working directly with Tpl., the tpl. mcp server is the bridge. MCP Server for Directus with Schema Management.

What Tpl. does

A Model Context Protocol (MCP) server for managing tasks in Directus with automatic schema synchronization. This server allows you to interact with your Directus PostgreSQL database through AI assistants like Claude or Cursor.

Key capabilities

  • Task Management — Create, read, update, and delete tasks
  • Schema Management — Automatically sync TypeScript models to Directus collections
  • Filtering — Filter tasks by status, priority, and other criteria
  • Validation — Built-in validation using Zod schemas
  • Type Safety — Full TypeScript support with proper typing

Tools it exposes

Once connected, the assistant can call this tool directly:

  • Debugging — The server logs errors to stderr. You can check the logs in your AI assistant's console or terminal

Installing the tpl. mcp server

The server is distributed via npm as npm, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 2 environment variables: DIRECTUS_URL, DIRECTUS_TOKEN. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  • Node.js 18+ - A Directus instance (local or hosted) - Directus API token or user credentials

Where it fits

Monitoring servers replace the paste-the-stack-trace ritual with an assistant that reads the real event, with all its surrounding context intact. Tpl. sits in that group, and the shape of its toolset — Debugging — tells you what it is really for. Worth comparing against the other monitoring security servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by creatuluw, written in TypeScript.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the tpl. mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
DebuggingThe server logs errors to stderr. You can check the logs in your AI assistant's console or terminal.

How to install the Tpl. MCP server

{
  "mcpServers": {
    "tpl": {
      "command": "npx",
      "args": ["-y", "npm"],
      "env": {
        "DIRECTUS_URL": "your-value",
        "DIRECTUS_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js 18+ - A Directus instance (local or hosted) - Directus API token or user credentials
VariableDescriptionRequired
DIRECTUS_URLEndpoint or connection string the server talks to.Yes
DIRECTUS_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Tpl. to Debugging.

Frequently asked questions

It connects Tpl. to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Debugging) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tpl. directly.