跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 Microsoft SQL Server，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
Summary
Query a Microsoft SQL Server database directly: list tables, describe columns and run read-only T-SQL. Supports SQL Server and Windows (NTLM) authentication. Installs read-only.
试试这样问
Microsoft SQL Server 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Microsoft SQL Server、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Microsoft SQL Server
Query a Microsoft SQL Server database directly: list tables, describe columns and run read-only T-SQL. Supports SQL Server and Windows (NTLM) authentication. Installs read-only.
设置
Setup
- Create a login and a database user with only
db_datareader:CREATE LOGIN amcp_reader WITH PASSWORD = 'change-me'; USE sales; CREATE USER amcp_reader FOR LOGIN amcp_reader; ALTER ROLE db_datareader ADD MEMBER amcp_reader; - Set
MSSQL_HOST,MSSQL_PORT(1433),MSSQL_DATABASE,MSSQL_USERandMSSQL_PASSWORD.
Windows authentication: set MSSQL_DOMAIN as well and the engine switches to NTLM instead of SQL Server auth. Leave it blank for a SQL login.
…(continued in the in-app connector instructions)
前提条件: MSSQL_HOST, MSSQL_PORT, MSSQL_DATABASE, MSSQL_USER, MSSQL_PASSWORD
本地安装连接器
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
打开 http://localhost:3000/connectors/store，选择 Microsoft SQL Server 并填入前提条件中列出的环境变量。
可用工具
| Tool | What it does |
|---|---|
mssql_list_tables | List the tables and views in the database with their schema and, where the server tracks it, an approximate row count |
mssql_describe_table | Describe one table: every column with its data type, nullability and default |
mssql_find_columns | Find columns across every table whose name matches a pattern — the fast way to locate where customer e-mail addresses, IBANs or order number |
mssql_query | Run a read-only SQL statement against Microsoft SQL Server and return up to 1000 rows |
mssql_query_examples | Show worked example queries for Microsoft SQL Server: how to list schemas, find large tables, inspect indexes and check what is running righ |
下一步
这份指南对你有帮助吗?
