What it does

Connects to databases and exposes querying to the agent, positioned as a multi-database client rather than a single-vendor connector. Convenient when your data is spread across engines. The usual rule applies harder here: read-only credentials, because this one can reach everywhere you configured.

Install

Terminal

npx -y @dbx-app/mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "dbx": {
      "command": "npx",
      "args": [
        "-y",
        "@dbx-app/mcp-server"
      ]
    }
  }
}

Use it for

Querying several databases from one client session

Skip it if

Production credentials with write scope

When to use it

Reach for this when the task needs database inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

DBX MCP