MCP Server for Directus with Schema Management
If you want an AI assistant working directly with Tpl., the tpl. mcp server is the bridge. MCP Server for Directus with Schema Management.
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.
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 terminalThe 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.
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.
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.
| Tool | What it does |
|---|---|
| Debugging | The server logs errors to stderr. You can check the logs in your AI assistant's console or terminal. |
{
"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.
| Variable | Description | Required |
|---|---|---|
| DIRECTUS_URL | Endpoint or connection string the server talks to. | Yes |
| DIRECTUS_TOKEN | Credential the server authenticates with. | Yes |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.