DBConvert Streams

listing.by

Run read-only SQL across PostgreSQL, MySQL, S3 buckets and local Parquet, CSV or JSON files in a single query.

state.local.long (state.local.title)listing.badge.runs_with

listing.install

listing.local.explain

npx -y @dbconvert/stream-mcp

listing.local.needs listing.local.note

listing.share.h

listing.share.p_local

mcp.tc/i/dbconvert-streams

listing.about

DBConvert Streams gives an AI assistant read-only access to PostgreSQL, MySQL, S3 storage and local data files. It can list connections, databases, schemas, tables and views, inspect table structure, and run SELECT queries that join data across different sources. The README describes 27 read-only tools, including schema and sample comparison and stream diagnostics. Only SELECT statements pass the server-side filter.

It runs locally over stdio, as the npm package @dbconvert/stream-mcp, a Docker image (slotix/stream-mcp), or an MCPB bundle for Claude extensions. You supply connection strings for your sources, such as postgres://user:password@host:5432/dbname, plus optional folders of data files. No hosted endpoint is used. The bundled server binary is proprietary software under the DBConvert Streams licence.

listing.can

  • Run read-only SQL across PostgreSQL, MySQL, S3 and files in one query
  • List connections, databases, schemas, tables and views
  • Inspect table columns and keys
  • Query Parquet, CSV and JSON files alongside databases
  • Compare schemas and data samples
  • Diagnose the status of migration and CDC streams

listing.tools

listing.notools.local

listing.prompts

  • Join orders.parquet with the customers table in Postgres and show 10 rows

  • List all tables in my MySQL shop database and describe the orders table

  • Compare the schema of my staging and production Postgres databases

  • Query the CSV files in my S3 bucket and count rows per month

listing.setup.h

listing.setup.local

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio dbconvert-streams -- npx -y @dbconvert/stream-mcp
  1. Start Claude Code and type /mcp. dbconvert-streams should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "dbconvert-streams": {
      "command": "npx",
      "args": [
        "-y",
        "@dbconvert/stream-mcp"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs Node.js on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "dbconvert-streams": {
      "command": "npx",
      "args": [
        "-y",
        "@dbconvert/stream-mcp"
      ]
    }
  }
}

Needs Node.js on your computer.

VS Code

Or from a terminal:

code --add-mcp '{"name":"dbconvert-streams","type":"stdio","command":"npx","args":["-y","@dbconvert/stream-mcp"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "dbconvert-streams": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@dbconvert/stream-mcp"
      ]
    }
  }
}

Needs Node.js on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "dbconvert-streams": {
      "command": "npx",
      "args": [
        "-y",
        "@dbconvert/stream-mcp"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add dbconvert-streams -- npx -y @dbconvert/stream-mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.dbconvert-streams]
command = "npx"
args = ["-y", "@dbconvert/stream-mcp"]

Needs Node.js on your computer.

Gemini CLI

gemini mcp add dbconvert-streams npx -- -y @dbconvert/stream-mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

{
  "mcpServers": {
    "dbconvert-streams": {
      "command": "npx",
      "args": [
        "-y",
        "@dbconvert/stream-mcp"
      ]
    }
  }
}

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs Node.js on your computer.

listing.faq

Can I paste mcp.tc/i/dbconvert-streams into my MCP client?

No. DBConvert Streams runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is npx -y @dbconvert/stream-mcp.

Does DBConvert Streams need an API key?

No. It doesn't declare any keys or environment variables. It runs with your user account's permissions, so check what its tools can reach.

Is DBConvert Streams a remote or a local server?

Local. Your client starts it as a process on your computer with npx -y @dbconvert/stream-mcp, which needs Node.js.

What can DBConvert Streams do?

You can run read-only SQL across PostgreSQL, MySQL, S3 and files in one query, list connections, databases, schemas, tables and views and inspect table columns and keys.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Who wrote this page?

mcp.tc's robot read DBConvert Streams's public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead_local listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![DBConvert Streams on mcp.tc](https://mcp.tc/i/dbconvert-streams/badge.svg)](https://mcp.tc/i/dbconvert-streams)
HTML
<a href="https://mcp.tc/i/dbconvert-streams"><img src="https://mcp.tc/i/dbconvert-streams/badge.svg" alt="DBConvert Streams on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/dbconvert-streams.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/dbconvert-streams" title="DBConvert Streams on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json_local

https://mcp.tc/i/dbconvert-streams.json

listing.em.fields

listing.disclaimer_checked