DBeaver Database MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_dbeaver_connectionsA | 列出DBeaver中已有且可用的PostgreSQL连接，并返回每个连接可进入的数据库摘要；不返回地址或账密。 |
| list_databasesA | 列出一个DBeaver PostgreSQL连接下当前账号可连接的全部数据库；返回默认库、模板库标志和注释。 |
| dbeaver_statusB | 验证一个DBeaver连接下的精确database、可见schemas、双重只读状态、服务端版本和硬限制；不返回地址或账密。 |
| list_schemasA | 列出一个DBeaver连接下精确database中的可见schema及每个schema的表、视图和对象计数。 |
| scan_databaseA | 扫描DBeaver连接内一个精确database/schema的表和视图目录，返回对象类型、注释、近似行数和计数；不读取业务行。 |
| search_catalogA | 按表名、字段名或注释搜索精确database目录；schema可省略以跨全部可见非系统schema搜索。 |
| get_table_contextA | 读取DBeaver连接内精确database/schema中的表或视图字段、注释、主外键、索引和近似行数；不读取业务行。 |
| analyze_queryA | 校验结构化查询的表、字段、权限和类型，返回查询结构摘要；不读取业务行。 |
| explain_queryA | 对服务端生成的结构化SELECT读取计划成本摘要；不运行ANALYZE，返回脱敏的计划树与成本，隐藏条件值。 |
| execute_queryB | 执行服务端组装的结构化SELECT；只读事务、账号原生读权限与RLS、依赖安全校验、参数绑定和有界结果。 |
| read_postgresql_logsA | 读取精确database的PostgreSQL当前JSON/CSV日志尾部；仅安全事件摘要，不接收路径或返回SQL/原始消息。 |
| read_database_settingsA | 读取当前账号可见的数据库配置，替代SHOW/SHOW ALL；敏感配置值脱敏。 |
| get_query_capabilitiesA | 查看结构化查询能力、参数语言和安全限制；不连接数据库。 |
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 13 tools
Tools are mostly clearly distinct along a database-exploration hierarchy (connections → databases → schemas → catalog → table context) plus a query lifecycle (analyze → explain → execute). Minor overlap exists between scan_database, search_catalog, and get_table_context, and between dbeaver_status and list_dbeaver_connections, but descriptions disambiguate them reasonably well.
Nearly all tools follow a consistent snake_case verb_noun pattern (list_databases, scan_database, get_table_context, execute_query, read_postgresql_logs). The lone outlier is 'dbeaver_status', which lacks a verb prefix and breaks the otherwise predictable convention.
13 tools is well-scoped for a read-only database exploration/inspection server covering connection, catalog, query, and diagnostic concerns. Each tool earns its place without obvious redundancy.
The read-only surface is comprehensive: connections, databases, schemas, catalog scan/search, table context, query analyze/explain/execute, plus logs and settings. Minor gaps exist (no dedicated index/constraint or view-listing tool, though these are partly folded into get_table_context), and write operations are intentionally absent.