io.github.dataplat/dbatools-mcp-server MCP Server
io.github.dataplat/dbatools-mcp-server
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.dataplat/dbatools-mcp-server MCP server?
MCP server for dbatools — exposes SQL Server management commands as MCP tools
How to install io.github.dataplat/dbatools-mcp-server
Copy-paste configuration for popular MCP clients.
DBATOOLS_SAFE_MODESet to 'false' to allow write/destructive dbatools operations. Defaults to true (read-only safe mode).
MAX_OUTPUT_ROWSMaximum number of rows returned per command. Defaults to 100. Allowed range: 1–10000.
COMMAND_TIMEOUT_SECONDSTimeout in seconds for each dbatools command. Defaults to 60. Allowed range: 5–3600.
PWSH_EXEPath to the PowerShell executable. Defaults to 'pwsh'.
{
"mcpServers": {
"dbatools-mcp-server": {
"command": "npx",
"args": [
"-y",
"dbatools-mcp-server"
],
"env": {
"DBATOOLS_SAFE_MODE": "<YOUR_DBATOOLS_SAFE_MODE>",
"MAX_OUTPUT_ROWS": "<YOUR_MAX_OUTPUT_ROWS>",
"COMMAND_TIMEOUT_SECONDS": "<YOUR_COMMAND_TIMEOUT_SECONDS>",
"PWSH_EXE": "<YOUR_PWSH_EXE>"
}
}
}
}Related MCP servers

D'AUBE // BRIDGE²
Universal AI skill compiler and MCP bridge. Write once, run across agents.

UML Forge
Architecture intelligence, security analysis, and living docs. 14 Mermaid tools.

Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.

Hashloom
Content-addressed contracts and a verification cache that cut agent context by skipping proven code.

DataRaum
Pre-computed metadata context engine for AI-driven data analytics
Observes tasks and generates anonymized SOPs — task tracking and SOP review via MCP. Fully local.
View repository →