A C# MCP server for interacting with databases via ADO.NET, compatible with Virtuoso.
MCP_AdoNet_Server.csproj
) is compatible with your environment by running:
dotnet run --framework net8.0 --project /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj
MCP_AdoNet_Server.csproj
) is compatible with your environment by running:
dotnet run --framework net9.0 --project /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj
MCP_AdoNet_Server.csproj
by running:
dotnet clean /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj
dotnet build /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj
Clone this repository:
git clone https://github.com/OpenLinkSoftware/mcp-adonet-server.git
cd mcp-adonet-server
Update your .env
by overriding the defaults to match your preferences
ADO_URL="HOST=localhost:1111;Database=Demo;UID=demo;PWD=demo"
API_KEY=xxx
For Claude Desktop users:
Add the following to claude_desktop_config.json
:
{
"mcpServers": {
"my_database": {
"command": "dotnet",
"args": ["run", "--framework", "net8.0", "--project", "/path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj"],
"env": {
"ADO_URL": "HOST=localhost:1111;Database=Demo;UID=demo;PWD=demo",
"API_KEY": "sk-xxx"
}
}
}
}
{
"mcpServers": {
"my_database": {
"command": "dotnet",
"args": ["run", "--framework", "net9.0", "--project", "/path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj"],
"env": {
"ADO_URL": "HOST=localhost:1111;Database=Demo;UID=demo;PWD=demo",
"API_KEY": "sk-xxx"
}
}
}
}
After successful installation, the following tools will be available to MCP client applications.
name | description |
---|---|
ado_get_schemas | List database schemas accessible to connected database management system (DBMS). |
ado_get_tables | List tables associated with a selected database schema. |
ado_describe_table | Provide the description of a table associated with a designated database schema. This includes information about column names, data types, nulls handling, autoincrement, primary key, and foreign keys |
ado_filter_table_names | List tables, based on a substring pattern from the q input field, associated with a selected database schema. |
ado_query_database | Execute a SQL query and return results in JSONL format. |
ado_execute_query | Execute a SQL query and return results in JSONL format. |
ado_execute_query_md | Execute a SQL query and return results in Markdown table format. |
ado_spasql_query | Execute a SPASQL query and return results. |
ado_sparql_query | Execute a SPARQL query and return results. |
ado_virtuoso_support_ai | Interact with the Virtuoso Support Assistant/Agent -- a Virtuoso-specific feature for interacting with LLMs |
ado_get_schemas
url
(string, optional): ADO.NET URL connection string.ado_get_tables
schema
(string, optional): Database schema to filter tables. Defaults to connection default.url
(string, optional): ADO.NET URL connection string.ado_filter_table_names
q
(string, required): The substring to search for within table names.schema
(string, optional): Database schema to filter tables. Defaults to connection default.url
(string, optional): ADO.NET URL connection string.ado_describe_table
schema
(string, required): The database schema name containing the table.table
(string, required): The name of the table to describe.url
(string, optional): ADO.NET URL connection string.ado_query_database
query
(string, required): The SQL query string to execute.url
(string, optional): ADO.NET URL connection string.ado_query_database_md
query
(string, required): The SQL query string to execute.url
(string, optional): ADO.NET URL connection string.ado_query_database_jsonl
query
(string, required): The SQL query string to execute.url
(string, optional): ADO.NET URL connection string.ado_spasql_query
query
(string, required): The SPASQL query string.max_rows
(number, optional): Maximum number of rows to return. Defaults to 20.timeout
(number, optional): Query timeout in milliseconds. Defaults to 30000.url
(string, optional): ADO.NET URL connection string.Demo.demo.execute_spasql_query
).ado_sparql_query
query
(string, required): The SPARQL query string.format
(string, optional): Desired result format. Defaults to 'json'.timeout
(number, optional): Query timeout in milliseconds. Defaults to 30000.url
(string, optional): ADO.NET URL connection string."UB".dba."sparqlQuery"
).ado_virtuoso_support_ai
prompt
(string, required): The prompt text for the AI function.api_key
(string, optional): API key for the AI service. Defaults to "none".url
(string, optional): ADO.NET URL connection string.DEMO.DBA.OAI_VIRTUOSO_SUPPORT_AI
).For easy troubleshooting:
Install the MCP Inspector:
npm install -g @modelcontextprotocol/inspector
Start the inspector:
dotnet clean /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj
npx @modelcontextprotocol/inspector dotnet run --framework net8.0 --project /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj -e ADO_URL="HOST=localhost:1111;Database=Demo;UID=username;PWD=password" -e API_KEY="sk-xxx-myapikey-xxx"
or
npx @modelcontextprotocol/inspector dotnet run --framework net9.0 --project /path/to/mcp-adonet-server/MCP_AdoNet_Server.csproj -e ADO_URL="HOST=localhost:1111;Database=Demo;UID=username;PWD=password" -e API_KEY="sk-xxx-myapikey-xxx"
depending on which .Net version is in use.
Access the provided URL to troubleshoot server interactions.
Access Mina blockchain data, including events, actions, and network state, through the Mina Archive Node API.
An MCP server for Quickbase, enabling seamless integration with AI assistants like Claude Desktop.
A simple MCP server for MySQL, demonstrating fundamental MCP protocol concepts. Requires a MySQL database connection configured via environment variables.
Securely query and retrieve data from your ThoughtSpot instance.
Manage NocoDB server, support read and write databases
A read-only MCP server for querying live Google Directory data using the CData JDBC Driver.
Integrates with Supabase to allow AI assistants to access and manage store data.
Access PubChem's database for chemical compounds, substances, and bioassays.
Stock market API made for AI agents
Inspect database schemas and execute queries on Google BigQuery.