Devart SQL MCP server
Commit Sep 3, 2026Enables AI clients to interact with SQL Server databases using natural language through ADO.NET or ODBC connectivity.
Also known as devart-ai-connectivity/devart-mcp-server-sqlserver, devart-mcp-server-sqlserver
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.1.0
- Last commit
- Sep 3, 2026
- License
- —
What is Devart SQL MCP?
Devart SQL enables AI clients to interact with SQL Server databases using natural language through ADO.NET or ODBC connectivity.
Summary generated from the project's README
About Devart SQL MCP server
Devart MCP Server for SQL Server allows AI clients to interact with SQL Server databases using natural language. It functions by translating user prompts into structured queries, which are then executed through Devart connectivity drivers. This server runs locally within your environment, ensuring that data remains inside your infrastructure, including Azure-connected instances with private networking.
Developers can choose between ADO.NET or ODBC connectivity. Building with ADO.NET utilizes the Devart dotConnect for SQL Server NuGet package, while the ODBC option requires the Devart ODBC Driver for SQL Server. The server supports transport protocols like stdio, where the AI client starts the server automatically, or http, which requires manual starting on a specific port. It is compatible with various AI clients including Claude Desktop, Cursor, Visual Studio Code, Windsurf, and Zed.
Setup involves configuring an mcpserver.json file with connection strings, DSN names, or license keys. While the MCP server itself is a free single-source project, connecting to the database requires a paid Devart ODBC Driver or ADO.NET provider.
What you can do with it
- 1Ad-hoc business reportingAsk questions about business data directly from the database without needing to build formal SSRS reports.
- 2Database administration assistanceUse AI to help investigate data issues, explore stored procedures, or troubleshoot performance problems.
- 3Enterprise data explorationAccess operational data from Microsoft Dynamics or ERP systems stored in SQL Server through AI tools.
- 4Non-technical data accessQuery data from databases that support .NET applications without requiring SQL knowledge or developer help.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
DEVART_MCP_SQLSERVER_CONNECTIONRequiredSecretA dotConnect for SQL Server connection string.
| Name | Description | |
|---|---|---|
| DEVART_MCP_SQLSERVER_CONNECTION | A dotConnect for SQL Server connection string. | RequiredSecret |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabledevart-ai-connectivity/devart-mcp-server-sqlserver is public and reachablegithub.com/devart-ai-connectivity/devart-mcp-server-sqlserve ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-09-17github.com/devart-ai-connectivity/devart-mcp-server-sqlserve ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubVersion 1.1.0
Devart MCP Server for SQL Server
Devart MCP Server for SQL Server enables AI clients to interact with your data through a secure server running in your environment. It turns a regular AI chat into a practical way to work with real-world business data — and it is faster than conventional export or manual querying.
Key benefits
Devart MCP Server for SQL Server allows you to:
- Work with data intuitively through natural language.
- Retrieve the required data for analysis within minutes.
- Report on your data faster with AI-powered assistance.
- Minimize manual data handling and integration maintenance.
How it works
Devart MCP Server for SQL Server helps AI clients communicate directly with SQL Server databases using natural-language prompts. It translates AI requests into structured queries, executes them through Devart connectivity drivers, and returns clean, structured results for seamless AI-powered data access.

Quick start
To get started with Devart MCP Server for SQL Server:
1. Download and install Devart ODBC Driver for SQL Server.
2. Download and install Devart MCP Server for SQL Server.
3. In Devart MCP Server for SQL Server, configure your data connection and integration settings.

4. Run your first natural-language query.
Manual installation and configuration
Prerequisites
Before building and running Devart MCP Server for SQL Server, ensure the following components are installed:
- .NET 8 SDK
- ADO.NET connection — Devart.AI.McpServer.AdoNet.SqlServer.csproj Devart dotConnect for SQL Server (installed automatically via NuGet during build)
- ODBC connection — Devart.AI.McpServer.Odbc.SqlServer.csproj Devart ODBC Driver for SQL Server (requires manual download and installation)
Step 1: Clone the repository
Clone the project repository and navigate to the project directory:
1. Open Command Prompt.
2. Enter the following command:
git clone https://github.com/devart-ai-connectivity/devart-mcp-server-sqlserver.git
cd devart-mcp-server-sqlserver
Step 2: Build the MCP Server from source
You can build Devart MCP Server for SQL Server from source using either of the supported database connectivity technologies: ADO.NET or ODBC.
- To build the MCP server with ADO.NET, run the following command:
dotnet publish Devart.AI.McpServer.AdoNet/Devart.AI.McpServer.AdoNet.SqlServer/Devart.AI.McpServer.AdoNet.SqlServer.csproj -c ReleaseSqlServer /p:TargetFramework=net8.0
The Devart dotConnect for SQL Server NuGet package is downloaded and restored automatically.
- To build the MCP server with ODBC, select the command based on the bitness of your data source.
For 64-bit data source, run the following command:
dotnet publish Devart.AI.McpServer.Odbc/Devart.AI.McpServer.Odbc.SqlServer/Devart.AI.McpServer.Odbc.SqlServer.csproj -c ReleaseSqlServer -r "win-x64" /p:TargetFramework=net8.0
For 32-bit data source, run the following command:
dotnet publish Devart.AI.McpServer.Odbc/Devart.AI.McpServer.Odbc.SqlServer/Devart.AI.McpServer.Odbc.SqlServer.csproj -c ReleaseSqlServer -r "win-x86" /p:TargetFramework=net8.0
Note
The target platform must match the bitness of your ODBC data source.
Step 3: Configure the database connection for the MCP Server
1. Create an mcpserver.json configuration file in the directory containing the built MCP Server executable.
2. In the file, configure the database connection.
- Configure a connection with ADO.NET.
Add the following configuration to the mcpserver.json file:
{
"Connections": [
{
"Name": "my_sqlserver",
"ConnectionString": "Server=localhost;User Id=your_user;Password=your_password;Database=your_database;License Key=your_license_key;",
"ProtocolType": "stdio"
}
]
}
- Configure a connection with ODBC.
Add the following configuration to the mcpserver.json file:
{
"Connections": [
{
"Name": "my_sqlserver",
"DsnName": "your_dsn_name",
"ProtocolType": "stdio"
}
]
}
- Configure a connection with ODBC using a connection string.
Add the following configuration to the mcpserver.json file:
{
"Connections": [
{
"Name": "my_sqlserver",
"ConnectionString": "Driver={Devart ODBC Driver for SQL Server};Server=localhost;User ID=sqlserver;Password=your_password;Database=your_database;",
"ProtocolType": "stdio"
}
]
}
where:
-
Name— The connection name. -
ConnectionString(applies to ADO.NET) — A database-specific connection string used to establish a connection to the target database. -
DsnName(applies to ODBC) — The name of your data source. -
ProtocolType— A transport protocol. The possible options are:stdioorhttp. -
HttpPort(required ifProtocolTypeis set tohttp) — The port number for thehttpprotocol.
Step 4: Run the MCP server
After you configure the MCP Server, you can start it.
Note
This step is required only when
ProtocolTypeis configured ashttp. If you use thestdiotransport protocol, your AI client starts the server automatically.
- To start the server with ADO.NET, run the following command:
Devart.AI.McpServer.AdoNet.SqlServer.exe run my_sqlserver
- To start the server with ODBC, run the following command:
Devart.AI.McpServer.Odbc.SqlServer.exe run my_sqlserver
where my_sqlserver is the name of the ODBC connection.
Step 5: Integrate with Claude Desktop
1. Open claude_desktop_config.json, the Claude configuration file.
Tip
If you can't locate the configuration file, it may not exist yet. To create it, open Claude Desktop and navigate to File > Settings > Developer, then click Edit Config. The folder with the
claude_desktop_config.jsonfile opens.
2. Add one of the following objects, depending on the transport protocol used by MCP Server:
- STDIO
{
"mcpServers": {
"devart": {
"command": "C:\\path\\to\\Devart.AI.McpServer.AdoNet.SqlServer.exe",
"args": [
"run",
"my_sqlserver"
]
}
}
}
where:
-
devartis the connector name that will appear in Claude Desktop. -
C:\\path\\to\\Devart.AI.McpServer.AdoNet.SqlServer.exeis the path to the executable file. For an ODBC connection, useDevart.AI.McpServer.Odbc.SqlServer.exe. -
my_sqlserveris the connection name specified in themcpserver.jsonconfiguration file. -
HTTP
"mcpServers": { "devart": { "command": "npx", "args": [ "-y", "mcp-remote", "http://localhost:5000/sse" ] } }where:
devartis the connector name that will appear in Claude Desktop.5000is the MCP Server listening port.
3. Save the file.
4. Restart Claude Desktop.
Devart MCP Server for SQL Server is now integrated with Claude, and devart appears in the Claude Desktop app in Customize > Connectors.
You can also integrate Devart MCP Server for SQL Server with other AI clients such as Cline, Codex, Cursor, Visual Studio Code, Windsurf, Zed.
Supported clients
Devart MCP Server for SQL Server supports integration with the following AI clients:
- Claude Desktop
- Visual Studio Code
- Cursor
- Codex
- Windsurf
- Cline
- Zed
- ...and other MCP-compatible AI clients
Typical use cases
Devart MCP Server for SQL Server is a practical fit for teams working with SQL Server as their primary data source.
-
.NET application data access
Query business data from SQL Server databases backing .NET web applications, APIs, and enterprise software, without SQL or developer involvement. -
Microsoft Dynamics and ERP analytics
Access CRM, ERP, and operational data stored in SQL Server by Microsoft Dynamics on-premises deployments directly through AI tools. -
SharePoint and intranet data exploration
Query content databases, list data, and metadata from SQL Server instances backing SharePoint or other Microsoft intranet platforms. -
BI and reporting without SSRS
Answer ad-hoc business questions directly from SQL Server databases without building SSRS reports or waiting for BI team involvement. -
Developer and DBA productivity
Help SQL Server developers and DBAs investigate data issues, explore stored procedures, audit schemas, and troubleshoot performance problems with AI assistance. -
Secure on-premises AI access to SQL Server
Keep SQL Server data inside your infrastructure, including Azure-connected instances with private networking, while enabling AI-driven analysis.
Licensing and activation
Devart MCP Server for SQL Server is distributed as a free single-source MCP server.
To connect to SQL Server, the server requires the corresponding Devart ODBC Driver for SQL Server, which is a paid product.
A 30-day free trial is available for the Devart ODBC Driver for SQL Server.
See the product page and documentation for the latest installation and activation details.
Support
Other Devart connectivity solutions
Devart SQL MCP questions
What are the prerequisites for building the server from source?
You need the .NET 8 SDK and either Devart dotConnect for SQL Server (for ADO.NET) or the Devart ODBC Driver for SQL Server.
Is the Devart MCP Server for SQL Server free?
The MCP server itself is distributed as a free single-source server, but connecting to SQL Server requires a paid Devart ODBC Driver or ADO.NET provider.
Which AI clients are supported?
It supports Claude Desktop, Visual Studio Code, Cursor, Codex, Windsurf, Cline, Zed, and other MCP-compatible clients.

