MySQL MCP Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_sql_queryA | 执行只读 SQL 查询（仅限 SELECT 语句） |
| create_tableC | 在 MySQL 数据库中创建新表 |
| insert_dataC | 向 MySQL 数据库表插入数据 |
| update_dataC | 更新 MySQL 数据库表中的数据 |
| delete_dataC | 从 MySQL 数据库表中删除数据 |
| execute_sqlA | 执行任意非 SELECT 的 SQL 语句（如 ALTER TABLE、DROP 等） |
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 6 tools
Each tool has a distinct and clear purpose with no overlap: create_table for table creation, delete_data for deletion, execute_sql for non-SQL operations, insert_data for insertion, run_sql_query for read-only queries, and update_data for updates. The separation between execute_sql (non-SELECT) and run_sql_query (SELECT) is particularly well-defined, preventing confusion.
All tool names follow a consistent verb_noun pattern in snake_case, such as create_table, delete_data, and run_sql_query. This uniformity makes the tool set predictable and easy for an agent to navigate, with no deviations in naming conventions.
With 6 tools, this server is well-scoped for basic MySQL database operations, covering essential CRUD actions and SQL execution. Each tool serves a specific function without redundancy, making the count appropriate for the domain and avoiding both over-saturation and under-coverage.
The tool set provides strong coverage for core database operations, including create, read (via run_sql_query), update, and delete, plus general SQL execution. A minor gap exists in lacking tools for table deletion or schema inspection, but agents can work around this using execute_sql for such tasks, keeping the surface largely complete for typical workflows.