MCP MS SQL Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DB_TYPE | Yes | Database type, must be 'mssql' | |
| MSSQL_PORT | No | SQL Server port, default 1433 | |
| MSSQL_USER | Yes | Database username | |
| MSSQL_SERVER | Yes | SQL Server address, e.g. tcp:your-server.database.windows.net | |
| MSSQL_ENCRYPT | No | Encrypt connection, default true | |
| QUERY_TIMEOUT | No | Query timeout in milliseconds, default 30000 | |
| MSSQL_DATABASE | Yes | Database name | |
| MSSQL_PASSWORD | Yes | Database password | |
| CONNECTION_POOL_MAX | No | Maximum connection pool size, default 10 | |
| CONNECTION_POOL_MIN | No | Minimum connection pool size, default 1 | |
| ALLOW_DELETE_OPERATION | No | Allow delete operations, default false | |
| ALLOW_INSERT_OPERATION | No | Allow insert operations, default false | |
| ALLOW_UPDATE_OPERATION | No | Allow update operations, default false | |
| ALLOW_WRITE_OPERATIONS | No | Allow write operations globally, default false | |
| MSSQL_TRUST_SERVER_CERTIFICATE | No | Trust server certificate, default true |
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 |
|---|---|
| sql_queryC | Execute a SQL query on the MS SQL Server database |
| get_database_infoA | Get information about the database server and available databases |
| show_tablesB | Show all tables in the current database |
| describe_tableC | Get detailed information about a table's structure |
| show_indexesC | Show indexes for a table or all tables |
| generate_analysis_notebookC | Generate a Jupyter notebook with Python code to analyze SQL query results |
| generate_visualizationB | Generate visualizations (bar, scatter, pie, line, heatmap, table) from SQL query results |
| generate_powerbi_visualizationC | Generate Power BI compatible data and visualization metadata |
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 8 tools
Each tool has a distinct purpose: query execution, metadata retrieval (tables, indexes, database info), and three different output generation types (notebook, PowerBI, general viz). No two tools overlap in functionality.
Most tools follow a verb_noun pattern (describe_table, generate_*, show_indexes, etc.) using lowercase snake_case. Slight inconsistency with 'sql_query' being noun-focused instead of verb_noun, but overall pattern is clear and predictable.
8 tools is appropriate for a database analysis server. It covers core needs (query, metadata, visualization) without being excessive or too sparse. The count is well within the ideal 3-15 range.
The tool set covers querying, table/index metadata, and generating analysis outputs. Minor gaps like listing views or stored procedures exist, but for the stated analysis purpose it is reasonably complete.