mcpField
M
mcp-server-get-database-config

mcp-server-get-database-config

Local
github.com/674019130Developer Tools0Updated 83w ago

About mcp-server-get-database-config

mcp-server-get-database-config creates a `database.json` file from a sample structure and database details. It is intended for MCP clients that need database configuration when generating simple analysis scripts.

Key features

  1. 01Create `database.json` from a sample
  2. 02Fill in database details
  3. 03Provide configuration for script generation

Use cases

  1. 01Prepare database settings for a Python analysis script
  2. 02Avoid manually adding configuration to an analysis prompt

MCP support

The MCP client can retrieve the generated database configuration for use while generating scripts.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-server-get-database-config

Create a new file named database.json based on the structure shown in the given sample file database-example.json, and fill in the database-related information.

With the following prompt, the MCP Client can automatically retrieve the database configuration, eliminating the need to manually provide it when generating simple analysis scripts, thereby improving Talk efficiency.

prompt

帮我写个python脚本,
在 db_alpha 库执行
select ex.device_id as id, ex.group_no
from service_config_alpha ex
where ex.is_active = 1
  and ex.status = 1
union all
select dv.id, dv.group_no
from device_config_beta dv
where dv.is_active = 1
  and dv.status = 1

语句,得到所有的服务端设备ID、所属组号(group_no)。

拿到这些 server,在 db_beta 库执行
select loc.region,
       count(1),
from connection_log cnt
         left join device_location loc on loc.id = cnt.client_id
where server_id in (
    # 这里填入单台 server 
)
group by loc.region

得到单台 server 的区域分布。但是拿到的结果中,有可能存在 region 为空的情况,这些是因为 connection_log 表中 client_id 并不在 db_beta 的 device_location 表中。

所以需要将这些 client_id 再拿到 db_alpha 库的 device_location 表中查询,将结果合并。
select loc.region,
       count(1)
       from device_location loc
       where loc.id in (
        # 这里填入单台 server 的区域分布结果中为空的 client_id
       )
       group by loc.region

最后,将两部分结果合并,得到单台 server 的区域分布。
计算区域分布的百分比,计算变异系数,使用 pyecharts 画单台 server 的区域分布百分比图。

再计算每个组的区域分布百分比,计算变异系数,使用 pyecharts 画每个组的区域分布百分比图。

再计算每个组的平均变异系数,使用 pyecharts 画每个组的平均变异系数柱状图。

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.