# DBConvert Streams (Federated SQL)

Runs read-only federated SQL across PostgreSQL, MySQL, S3 buckets, and local Parquet or CSV files directly from your AI coding assistant.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 24
- Author: slotix
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/slotix/dbconvert-streams-public
- Updated: 2026-09-05
- HTML: https://affpapa.org/en/nevibecode/mcp/dbconvert-streams-federated-sql

## What it does

This MCP server lets AI assistants inspect database schemas and run federated queries across multiple engines at once. You can link PostgreSQL, MySQL, S3 storage, and directories with Parquet or CSV files inside one session. Cross-database joins work without intermediate data dumps.

Write operations are completely blocked. The server strictly filters commands so that only `SELECT` queries run, preventing the assistant from altering tables or modifying data rows.

While documentation and examples use the MIT license, the underlying DBConvert Streams binary is proprietary software. Running the server via CLI commands requires `npx` from Node.js, or the `slotix/stream-mcp` container in Docker.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add streams -- npx -y @dbconvert/stream-mcp
```

### Codex

**Platform CLI**
```bash
codex mcp add dbconvert-streams-federated-sql -- npx -y @dbconvert/stream-mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "dbconvert-streams-federated-sql": {
            "command": "npx",
            "args": [
                "-y",
                "@dbconvert/stream-mcp"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "dbconvert-streams-federated-sql": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@dbconvert/stream-mcp"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add dbconvert-streams-federated-sql npx -y @dbconvert/stream-mcp
```

## When to use it
- Join PostgreSQL and MySQL tables with local Parquet files in one SQL query
- Inspect schemas across multiple production databases without pasting DDL
- Query S3 buckets and local CSV or JSON data without manual import steps
- Audit database contents safely under an enforced read-only execution policy

## Example prompts
- List all active database connections and show the schema for the customers table.
- Join records from `orders.parquet` with the PostgreSQL customer table and return the top 10 rows.
- Compare the table structure between the MySQL and PostgreSQL connections.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md