dm_mcp_server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DAMENG_HOST | Yes | 达梦数据库主机地址 | |
| DAMENG_PORT | No | 达梦数据库端口 | 5236 |
| DAMENG_USER | Yes | 数据库用户名 | |
| DAMENG_SCHEMA | No | MCP 服务默认使用的 Schema | |
| DAMENG_PASSWORD | Yes | 数据库密码 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| test_connectionA | 测试数据库连接状态 |
| batch_comment_columns_sqlA | 批量执行字段注释 SQL，仅允许 COMMENT ON COLUMN 语句 参数: sql: 多条 COMMENT ON COLUMN 语句，可用分号分隔 stop_on_error: 执行阶段遇到错误是否停止 |
| execute_sql_fileA | 读取并执行 SQL 文件，用于处理超长 SQL。 文件路径必须位于 DAMENG_SQL_FILE_ALLOWED_DIRS 白名单目录内。 文件中的 SQL 注释会在校验和执行前剥离，字符串字面量内的内容不受影响。 |
| get_sql_file_allowed_dirsA | 获取 execute_sql_file 允许读取的 SQL 文件目录。 |
| execute_sqlC | 执行 SQL 语句（强制限定配置下的SCHEMA操作） 参数: sql: 要执行的 SQL 语句 fetch_results: 是否返回查询结果（默认 True） limit: 限制返回的行数，用于分页（可选） offset: 跳过的行数，用于分页（可选） |
| list_tablesA | 查询指定SCHEMA下的所有表，不指定则查询默认SCHEMA |
| count_tablesA | 统计指定SCHEMA下的表数量，不指定则统计默认SCHEMA |
| get_current_schemaB | 获取当前配置的数据库的SCHEMA及允许的SCHEMA列表 |
| switch_schemaB | 切换当前操作的SCHEMA（仅在配置了DAMENG_ALLOWED_SCHEMAS时可用） |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: connection testing, direct SQL execution, file-based SQL execution, table listing/counting, schema inspection/switching, batch column comments, and file-directory introspection. Although multiple tools execute SQL, their input modes and constraints are explicit enough to avoid misselection.
All tool names follow a consistent snake_case verb_noun pattern, such as test_connection, list_tables, switch_schema, and execute_sql_file. Even the more specialized batch_comment_columns_sql follows the same imperative style.
Nine tools is well-scoped for a database MCP server. Each tool covers a meaningful part of the workflow, from schema navigation to SQL execution, without feeling bloated or redundant.
The core database operations are covered: connection testing, SQL execution, schema switching, and table listing. A minor gap is the lack of a dedicated describe-table or column-metadata tool, though this can be worked around with execute_sql.