PluginBench
MCP Server
Active
MIT

io.github.dataplat/dbatools-mcp-server MCP Server

io.github.dataplat/dbatools-mcp-server

RepositoryRegistry
How to choose

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.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • DBATOOLS_SAFE_MODE

    Set to 'false' to allow write/destructive dbatools operations. Defaults to true (read-only safe mode).

  • MAX_OUTPUT_ROWS

    Maximum number of rows returned per command. Defaults to 100. Allowed range: 1–10000.

  • COMMAND_TIMEOUT_SECONDS

    Timeout in seconds for each dbatools command. Defaults to 60. Allowed range: 5–3600.

  • PWSH_EXE

    Path to the PowerShell executable. Defaults to 'pwsh'.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "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

Universal AI skill compiler and MCP bridge. Write once, run across agents.

1
Python
MIT
View repository →
UMUML Forge logo

UML Forge

Active

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

0
Python
MIT
View repository →

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

4
TypeScript
Apache-2.0
View repository →
HAHashloom logo

Hashloom

Active

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

2
Python
Apache-2.0
View repository →
DADataRaum logo

DataRaum

Active

Pre-computed metadata context engine for AI-driven data analytics

3
Python
Apache-2.0
View repository →

Observes tasks and generates anonymized SOPs — task tracking and SOP review via MCP. Fully local.

View repository →