How do I use SQL Server MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SQL Server MCP describe the Orders table in the Sales schema" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

SQL Server MCP

Q: Which integrations are available for this server?

Allows GitHub Copilot to explore database schemas and execute read-only queries on SQL Server databases.

by az-coder-123

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

SQL Server MCP

An MCP (Model Context Protocol) server that connects AI assistants to Microsoft SQL Server databases. Enables AI tools like GitHub Copilot, Cursor, Cline, Claude Desktop, and Claude Code to explore database schemas and execute read-only queries safely.

Features

29 built-in tools for comprehensive database analysis and management
Read-only by design — uses db_datareader role, blocks all destructive SQL
SQL injection protection — AST-based query validation + keyword blocklist
Automatic row limits — prevents memory overflow with smart TOP N injection
AI-friendly errors — structured error responses with actionable suggestions
Schema caching — 1-hour TTL metadata cache reduces redundant DB calls
Unicode/Vietnamese support — full NVARCHAR UTF-8 passthrough
Dual transport — stdio (default) for local AI tools, HTTP/SSE for web clients
Data analysis — table statistics, index information, and column distribution
Data export — export table data to JSON or CSV format
Complete schema understanding — views, constraints, stored procedures, and server info
Security auditing — user management and permission analysis
Enhanced profiling — detailed column distribution with pattern recognition
Dependency mapping — full dependency analysis for tables and columns
Schema management — comprehensive schema organization and analysis
Data quality validation — integrity checks and comprehensive profiling
Documentation automation — generate schema documentation and ER diagrams

Related MCP server: DBMCP

Available Tools

Database & Schema (3 tools)

Tool	Description
`list_databases`	List all user-accessible databases on the SQL Server instance
`list_schemas`	List all schemas in database with table and view counts
`list_tables`	List tables and views in a specific schema

Schema Exploration (5 tools)

Tool	Description
`describe_table`	Get column details: name, type, nullable, PK, description
`get_table_relationships`	Get foreign key mappings for a table (guides JOINs)
`search_tables`	Search tables/columns/descriptions by keyword
`get_view_definition`	Get SQL definition of a view along with referenced tables
`list_constraints`	List all constraints (PK, FK, Unique, Check) for a table

Data Analysis (6 tools)

Tool	Description
`get_table_statistics`	Get table statistics including row count, size, and timestamps
`get_table_indexes`	Get all indexes for a table with column details
`analyze_table`	Analyze table data to get distribution statistics for each column
`get_column_distribution`	Get detailed distribution statistics for a specific column with pattern recognition
`list_stored_procedures`	List all stored procedures and functions with parameters
`get_procedure_definition`	Get full SQL definition of a stored procedure or function

Dependencies & Usage (2 tools)

Tool	Description
`get_table_dependencies`	Get full dependency map for a table (what it depends on and what depends on it)
`get_column_usage`	Get detailed usage information for a specific column (views, procedures, foreign keys, indexes)

Data Quality (2 tools)

Tool	Description
`validate_data_integrity`	Validate data integrity for a table (FK violations, duplicates, null violations)
`get_data_profile`	Get comprehensive data profile for a table including quality metrics

Documentation (3 tools)

Tool	Description
`generate_schema_documentation`	Generate comprehensive schema documentation with tables, views, columns, and relationships
`create_entity_relationship_diagram`	Create entity relationship diagram in Mermaid, PlantUML, or DOT format
`generate_api_documentation`	Generate REST API documentation from database schema with inferred endpoints and schemas

Migration & Comparison (2 tools)

Tool	Description
`create_migration_scripts`	Generate migration scripts for schema changes with up/down migrations
`compare_schemas`	Compare two schemas to identify differences in tables, views, and procedures

Server & System (1 tool)

Tool	Description
`get_server_info`	Get SQL Server information including version, edition, and status

Security & Users (2 tools)

Tool	Description
`list_users`	List all database users and their roles
`get_user_permissions`	Get detailed permissions for a specific user

Data Export & Query (3 tools)

Tool	Description
`execute_read_query`	Execute a validated read-only SELECT query
`export_table_data`	Export table data to JSON or CSV format
`clear_cache`	Clear the metadata cache to force fresh data

Quick Start

1. Install

git clone https://github.com/az-coder-123/sql-server-mcp.git
cd sql-server-mcp
npm install
npm run build

2. Configure

Copy the environment template and fill in your SQL Server credentials:

cp .env.example .env

Edit .env:

DB_HOST=localhost
DB_PORT=1433
DB_NAME=MyDatabase
DB_USER=readonly_user
DB_PASSWORD=your_password
DB_ENCRYPT=true
DB_TRUST_SERVER_CERT=false

Important: The DB_USER should have the db_datareader role only. The server blocks all write operations at the code level, but defense-in-depth at the database level is strongly recommended.

3. Run

# stdio mode (default — for AI tools)
npm start

# Development mode (with hot reload)
npm run dev

# HTTP/SSE mode (for web clients)
MCP_TRANSPORT=http npm start

Integration with AI Tools

GitHub Copilot (VS Code)

Create .vscode/mcp.json in your project:

{
  "servers": {
    "sql-server-mcp": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/sql-server-mcp/dist/index.js"],
      "env": {
        "DB_SERVER": "localhost",
        "DB_DATABASE": "MyDatabase",
        "DB_USER": "readonly_user",
        "DB_PASSWORD": "${input:dbPassword}"
      }
    }
  }
}

VS Code will securely prompt for the password at runtime via ${input:dbPassword}.

Cursor

Create .cursor/mcp.json:

{
  "mcpServers": {
    "sql-server-mcp": {
      "command": "node",
      "args": ["/path/to/sql-server-mcp/dist/index.js"],
      "env": {
        "DB_SERVER": "localhost",
        "DB_DATABASE": "MyDatabase",
        "DB_USER": "readonly_user",
        "DB_PASSWORD": "your_password"
      }
    }
  }
}

Cline (VS Code Extension)

Open Cline settings in VS Code
Go to MCP Servers → Add Server
Select Command (stdio)
Enter:
- Command: node
- Args: /path/to/sql-server-mcp/dist/index.js
- Env: DB_SERVER=localhost, DB_DATABASE=MyDatabase, DB_USER=readonly_user, DB_PASSWORD=your_password

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %AppData%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "sql-server-mcp": {
      "command": "node",
      "args": ["/path/to/sql-server-mcp/dist/index.js"],
      "env": {
        "DB_SERVER": "localhost",
        "DB_DATABASE": "MyDatabase",
        "DB_USER": "readonly_user",
        "DB_PASSWORD": "your_password"
      }
    }
  }
}

Claude Code (CLI)

claude --mcp-config ./mcp-config.json "Show me all tables in database"

Where mcp-config.json uses the same mcpServers format as Claude Desktop above.

Configuration Reference

All settings are configured via environment variables (or .env file):

Variable	Default	Description
`DB_HOST`	`localhost`	SQL Server hostname or IP
`DB_PORT`	`1433`	SQL Server port
`DB_NAME`	`master`	Default database
`DB_USER`	—	SQL Server login username
`DB_PASSWORD`	—	SQL Server login password
`DB_ENCRYPT`	`true`	Enable TLS encryption
`DB_TRUST_SERVER_CERT`	`false`	Trust self-signed certificates
`MCP_TRANSPORT`	`stdio`	Transport mode: `stdio` or `http`
`MCP_HTTP_PORT`	`3000`	HTTP server port (when `MCP_TRANSPORT=http`)
`QUERY_ROW_LIMIT`	`100`	Max rows returned per query (auto-injected)
`QUERY_TIMEOUT_MS`	`30000`	Query timeout in milliseconds
`PAYLOAD_MAX_BYTES`	`1048576`	Max response payload size (1MB)
`SCHEMA_CACHE_TTL_SECONDS`	`3600`	How long schema metadata is cached

Security

This server is designed for read-only database access with multiple layers of protection:

Database-level: Uses a db_datareader-only account with readOnlyIntent connection flag
Query validation: AST-based parsing via node-sql-parser (with regex fallback for T-SQL edge cases)
Keyword blocklist: INSERT, UPDATE, DELETE, DROP, EXEC, TRUNCATE, ALTER, CREATE, GRANT, REVOKE, MERGE and more
Multi-statement blocking: Semicolons outside string literals are rejected
Row limiting: Automatic TOP N injection prevents memory exhaustion
Payload truncation: Responses exceeding 1MB are truncated with a warning
Connection timeout: 30-second hard timeout on all queries

Project Structure

sql-server-mcp/
├── src/
│   ├── index.ts                          # Server entry point, tool registration, transport
│   ├── config/database.ts                   # Connection pool, env vars
│   ├── tools/
│   │   ├── schemaTools.ts                 # list_databases, list_tables, describe_table, relationships, search
│   │   ├── schemaManagementTools.ts        # list_schemas
│   │   ├── queryTools.ts                  # execute_read_query
│   │   ├── tableStatisticsTools.ts          # get_table_statistics
│   │   ├── tableIndexTools.ts             # get_table_indexes
│   │   ├── tableAnalysisTools.ts          # analyze_table
│   │   ├── columnTools.ts                # get_column_distribution
│   │   ├── storedProcedureTools.ts          # list_stored_procedures
│   │   ├── exportTools.ts                 # export_table_data
│   │   ├── viewTools.ts                   # get_view_definition
│   │   ├── constraintTools.ts              # list_constraints
│   │   ├── serverInfoTools.ts             # get_server_info
│   │   ├── procedureDefinitionTools.ts     # get_procedure_definition
│   │   ├── userTools.ts                   # list_users, get_user_permissions
│   │   ├── dependencyTools.ts            # get_table_dependencies
│   │   ├── usageTools.ts                 # get_column_usage
│   │   ├── dataIntegrityTools.ts         # validate_data_integrity
│   │   ├── dataProfileTools.ts          # get_data_profile
│   │   ├── documentationTools.ts         # generate_schema_documentation
│   │   ├── apiDocumentationTools.ts     # generate_api_documentation
│   │   ├── migrationTools.ts            # create_migration_scripts
│   │   ├── schemaComparisonTools.ts     # compare_schemas
│   │   └── diagramTools.ts              # create_entity_relationship_diagram
│   ├── types/index.ts                     # Shared TypeScript interfaces
│   ├── utils/
│   │   ├── sqlValidator.ts                # AST + regex query validation, TOP injection
│   │   └── errorMapper.ts                 # SQL error code → AI-friendly messages
│   └── cache/schemaCache.ts              # In-memory TTL cache
├── tests/                                # Unit tests (vitest)
├── dist/                                 # Compiled output (npm run build)
├── .env.example                          # Environment variable template
└── package.json

Development

# Install dependencies
npm install

# Run in dev mode (hot reload)
npm run dev

# Run tests
npm test

# Build for production
npm run build

License

ISC

Available Tools

49 tools

analyze_normalization_levelB

Analyze normalization level of tables using heuristic approach (1NF, 2NF, 3NF detection)

Inputs: schema, tableName.

analyze_query_performanceB

Analyze query performance using execution statistics DMVs to find slow queries and bottlenecks

Inputs: topN, schema.

analyze_schema_change_impactB

Analyze impact of schema changes by finding all dependent objects

Inputs: tableName (required), schema.

analyze_tableC

Analyze table data to get distribution statistics for each column

Inputs: tableName (required), schema.

audit_user_permissionsC

Audit user permissions for security analysis and compliance

Inputs: userName.

backup_databaseB

Backup a SQL Server database to a .bak file with optional compression

Inputs: backupPath (required), databaseName (required), backupType, description.

check_database_connectionsA

Check active connections to a database (useful before restore)

Inputs: databaseName.

clear_cacheA

Clear the schema metadata cache to force fresh data from the database

Inputs: no named parameters.

compare_schemasA

Compare two schemas to identify differences in tables, views, and procedures

Inputs: sourceSchema, targetSchema, targetDatabase.

create_databaseA

Create a new SQL Server database with specified options

Inputs: databaseName (required), collation, maxSizeMB, fileGrowthMB, +1 more.

create_entity_relationship_diagramA

Create entity relationship diagram in Mermaid, PlantUML, or DOT format

Inputs: schema (required), format, includeViews.

create_migration_scriptsB

Generate migration scripts for schema changes with up/down migrations

Inputs: changes (required), schema.

describe_tableA

Get column details (name, type, PK, description) for a table

Inputs: tableName (required), schema.

detect_circular_dependenciesA

Detect circular dependencies in foreign key relationships

Inputs: schema.

disconnect_database_usersA

Disconnect all users from a database by setting access mode (useful before restore)

Inputs: databaseName (required), mode, rollbackImmediate.

execute_read_queryA

Execute a read-only SQL SELECT query (automatically validated and row-limited)

Inputs: sqlQuery (required).

export_table_dataB

Export table data to JSON or CSV format

Inputs: format (required), tableName (required), limit, schema, +1 more.

find_unused_stored_proceduresA

Find stored procedures that are not executed recently or never executed

Inputs: schema, unusedDays.

generate_api_documentationB

Generate REST API documentation from database schema with inferred endpoints and schemas

Inputs: schema, baseUrl, includeProcedures.

generate_schema_documentationB

Generate comprehensive schema documentation with tables, views, columns, and relationships

Inputs: schema, includeViews.

get_backup_file_listB

Get the list of data and log files contained in a backup file

Inputs: backupPath (required).

get_backup_headerA

Get backup metadata and header information from a .bak file

Inputs: backupPath (required).

get_column_distributionC

Get detailed distribution statistics for a specific column

Inputs: tableName (required), columnName (required), topN, schema, +1 more.

get_column_usageA

Get detailed usage information for a specific column (views, procedures, foreign keys, indexes)

Inputs: tableName (required), columnName (required), schema.

get_database_summaryB

Get comprehensive summary of a database including statistics, size, schemas, and last backup

Inputs: databaseName (required).

get_data_profileB

Get comprehensive data profile for a table including quality metrics

Inputs: tableName (required), schema, sampleSize.

get_procedure_definitionA

Get the full SQL definition of a stored procedure or function

Inputs: procedureName (required), schema.

get_server_infoA

Get SQL Server information including version, edition, and status

Inputs: no named parameters.

get_table_dependenciesB

Get full dependency map for a table (what it depends on and what depends on it)

Inputs: tableName (required), schema.

get_table_indexesB

Get all indexes for a table with column details

Inputs: tableName (required), schema.

get_table_relationshipsA

Get foreign key relationships for a table (helps with JOINs)

Inputs: tableName (required), schema.

get_table_statisticsC

Get table statistics including row count, size, and timestamps

Inputs: tableName (required), schema.

get_user_permissionsC

Get detailed permissions for a specific user

Inputs: userName (required), objectType.

get_view_definitionA

Get the SQL definition of a view along with referenced tables

Inputs: viewName (required), schema.

kill_database_sessionsB

Kill specific sessions connected to a database

Inputs: databaseName (required), sessionIds.

list_backupsA

List recent backup history from msdb, optionally filtered by database name

Inputs: databaseName.

list_constraintsA

List all constraints (PK, FK, Unique, Check) for a table or all tables

Inputs: schema, tableName.

list_databasesA

List all user-accessible databases on SQL Server instance

Inputs: no named parameters.

list_schemasA

List all schemas in database with table and view counts

Inputs: no named parameters.

list_stored_proceduresA

List all stored procedures and functions with parameters

Inputs: schema.

list_tablesC

List all tables and views in a database schema

Inputs: schema.

list_tables_allA

List all tables across all databases or in a specific database

Inputs: databaseFilter.

list_triggersB

List all triggers in the database with details and dependencies

Inputs: schema.

list_usersA

List all database users and their roles

Inputs: no named parameters.

restore_databaseB

Restore a SQL Server database from a .bak file

Inputs: backupPath (required), databaseName (required), fileMoves, withReplace, +1 more.

search_across_databasesB

Search for tables, columns, or procedures across all databases by keyword

Inputs: keyword (required), searchIn.

search_tablesB

Search for tables/columns/descriptions matching a keyword

Inputs: keyword (required).

suggest_index_optimizationsB

Analyze and suggest index improvements including missing, unused, and fragmented indexes

Inputs: topN, schema.

validate_data_integrityB

Validate data integrity for a table (FK violations, duplicates, null violations)

Inputs: tableName (required), schema, checkFK, checkNulls, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

B3.2/5.0

Scored 2026-08-01 03:20 across 49 tools

Disambiguation3/5

Many tools have specific purposes, but there is overlap in analysis tools like analyze_table, get_column_distribution, and get_data_profile that could be confused. Similarly, list_tables and list_tables_all differ only in scope. Descriptions help clarify, but the large tool count creates ambiguity.

Naming Consistency4/5

Tools consistently follow a snake_case verb_noun pattern (e.g., describe_table, list_tables, backup_database). Minor deviations include the 'all' suffix in list_tables_all and some verbs like 'check' vs 'disconnect' for similar operations, but overall the convention is consistent and readable.

Tool Count2/5

With 49 tools, the server is over the typical threshold for a well-scoped MCP server. While the SQL Server domain is broad, many tools could be consolidated (e.g., multiple analysis and statistics tools). This heavy count may overwhelm agents and increase selection errors.

Completeness3/5

The server covers a wide range of operations including schema exploration, querying, performance analysis, documentation generation, and backup/restore. However, it lacks tools for DDL/DML operations (e.g., create table, update data) and provides no way to modify objects, limiting its usefulness for full database management.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

SQL Server MCP by InsightfulPipeA
com.insightfulpipe
Hosted SQL Server MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Databases Developer Tools
41
https://mssql.insightfulmcp.com/
DraxlrA
com.draxlr.api
Draxlr's remote MCP server connects AI assistants to your SQL databases and dashboards. Explore schemas, run read-only queries, manage saved queries and dashboards, and export results, all with row-level security so each user sees only their own data.
Data Visualization Databases Search
1
https://api.draxlr.com/mcp
AI2SQL
io.ai2sql
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Databases Developer Tools
1
https://builder.ai2sql.io/api/chatgpt-mcp
CData Connect AI
com.cdata
Cloud-hosted MCP server for secure AI access to enterprise data sources via CData Connect AI.
Databases RAG Systems Cloud Platforms
2
https://mcp.cloud.cdata.com/mcp

Related MCP Servers

mcp-sqlserver
Databases Developer Tools Monitoring
gunvertugberk
A
license
B
quality
D
maintenance
A powerful MCP server for Microsoft SQL Server that connects AI assistants directly to your SQL Server databases with enterprise-grade security controls.
Updated 7 months ago (2026-04-13 20:28 UTC)
38
40 npm
3
MIT
DBMCP
Databases RAG Systems
jesse-smith
A
license
A
quality
D
maintenance
MCP server providing read-only access to SQL Server databases for AI assistants, enabling schema exploration, query execution, and foreign key inference with token-efficient TOON responses.
Updated 5 months ago (2026-06-15 06:32 UTC)
9
1
MIT
mssql-mcp
Databases Developer Tools
eamonboyle
A
license
Not graded
quality
B
maintenance
An MCP server that enables AI assistants to query and manage Microsoft SQL Server databases using natural language.
Updated a month ago (2026-10-10 16:14 UTC)
117 npm
5
MIT
SQL Server MCP
Databases RAG Systems
TharanaBope
A
license
Not graded
quality
D
maintenance
Cross-platform MCP server for SQL Server that enables AI assistants to explore schemas, relationships, and run read-only queries via natural language.
Updated 7 months ago (2026-04-23 08:13 UTC)
1
MIT

SQL Server MCP

Features

Available Tools

Database & Schema (3 tools)

Schema Exploration (5 tools)

Data Analysis (6 tools)

Dependencies & Usage (2 tools)

Data Quality (2 tools)

Documentation (3 tools)

Migration & Comparison (2 tools)

Server & System (1 tool)

Security & Users (2 tools)

Data Export & Query (3 tools)

Quick Start

1. Install

2. Configure

3. Run

Integration with AI Tools

GitHub Copilot (VS Code)

Cursor

Cline (VS Code Extension)

Claude Desktop

Claude Code (CLI)

Configuration Reference

Security

Project Structure

Development

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

mcp-sqlserver

DBMCP

mssql-mcp

SQL Server MCP