SQL Benchmarks Lab MCP Server

What the code does

We read the source, 4 d ago · rules 995398eba69f

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

                AgentTrace._standalone_dirs[key] = os.path.join(
                    AGENT_RUNS_DIR,
                    f"standalone_{datetime.now(timezone.utc).strftime('%Y%m%d_%H%M%S')}")

                        select = mandatory_names + list(subset)

            p = subprocess.run(cmd, cwd=ROOT_DIR, env=local_env,

        <script charset="utf-8" src="https://cdn.plot.ly/plotly-3.6.0.min.js" integrity="sha256-QaOVwtVY0T02VaHrr6pnoHLCwayMJp4O5n4YyaE3rJk=" crossorigin="anonymous"></script>                <div id="b410f763-d51b-4f9d-b5c0-d0add29aba60" class="plotly-graph-div" style="height:100…

    ssh_key_path: str = os.getenv("ACTIAN_SSH_KEY", os.path.expanduser("~/.ssh/benchmark-key-pair.pem"))

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add sqlbenchdag -- uvx sqlbenchdag

{
  "mcpServers": {
    "sqlbenchdag": {
      "command": "uvx",
      "args": [
        "sqlbenchdag"
      ]
    }
  }
}

[mcp_servers.sqlbenchdag]
command = "uvx"
args = ["sqlbenchdag"]

{
  "mcpServers": {
    "sqlbenchdag": {
      "command": "uvx",
      "args": [
        "sqlbenchdag"
      ]
    }
  }
}

{
  "servers": {
    "sqlbenchdag": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "sqlbenchdag"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: SB_RESULTS_DIR (Directory of experiment result capsules. The package ships the SQL suites, taxonomy and templates but NOT capsules, which are run output — so on a fresh install the catalog tools work and list_results is empty until this points at a results directory), SB_API_BASE (Optional. Base URL of a running SQL Benchmarks REST API. Leave unset and the read tools mount the API in-process — no server needed. Set it only when the API runs elsewhere, or to use submit_experiment, which needs a process that outlives the request).