sql-server-mcp

# sql-server-mcp A local MCP server for read-only SQL Server / MS Fabric queries. Runs as a single-user process over stdio, authenticated as *you* (delegated Entra ID identity, not a service principal) — **one server process per tenant**. ## Prerequisites - Python 3.14+ and [uv](https://docs.astral.sh/uv/) - Either the [Azure CLI](https://learn.microsoft.com/cli/azure/install-azure-cli) logged in to the target tenant (`az login --tenant <tenant-id>`), or just a browser available — the server falls back to an interactive browser login if there's no CLI session - An Entra ID account in the target tenant with read access to the target database (e.g. `db_datareader`) ## Configuration Each tenant gets its own set of environment variables: | Variable | Required | Description | |---|---|---| | `MCP_SQL_SERVER_NAME` | yes | SQL Server / Fabric SQL endpoint hostname, e.g. `xyz-xyz.datawarehouse.fabric.microsoft.com` | | `MCP_SQL_DATABASE_NAME` | yes | Default database to connect to | | `MCP_AZURE_TENANT_ID` | yes | The Entra ID tenant ID — pins auth to this directory even if your machine has other `az login` sessions active | | `MCP_MAX_ROWS` | no | Max rows returned per tool call (default: 25) | ## Running it The server is a `uvx`-runnable console script (`sql-server-mcp`), no manual install step needed - `uvx` builds an isolated environment for it on first run and reuses it afterwards: ```bash uvx sql-server-mcp ``` To run from a local checkout instead (e.g. during development), point `--from` at the path: ```bash uvx --from /path/to/sql-server-mcp sql-server-mcp ``` On startup it acquires a token (via `az login` if available, otherwise an interactive browser prompt) and runs over stdio. Database connectivity uses [`mssql-python`](https://github.com/microsoft/mssql-python), which bundles its own driver — no separate ODBC driver install is required. ### Example MCP client config One block per tenant: ```json { "mcpServers": { "tenant-a-sql": { "…