A lightweight Java-based MCP (Model Context Protocol) server for JDBC built with Quakrus. This server is compatible with Virtuoso DBMS and any other DBMS backend that has a JDBC driver.
MCP server requires Java 21 or above.
Clone this repository:
git clone https://github.com/OpenLinkSoftware/mcp-jdbc-server.git cd mcp-jdbc-server
Update your .env
by overriding these defaults to match your preferences:
jdbc.url=jdbc:virtuoso://localhost:1111
jdbc.user=dba
jdbc.password=dba
jdbc.api_key=xxx
For Claude Desktop users using Virtuoso and its JDBC driver:
Add the following to claude_desktop_config.json
:
{ "mcpServers": { "my_database": { "command": "java", "args": ["-jar", "/path/to/mcp-jdbc-server/MCPServer-1.0.0-runner.jar"], "env": { "jdbc.url": "jdbc:virtuoso://localhost:1111", "jdbc.user": "username", "jdbc.password": "password", "jdbc.api_key": "sk-xxx" } } } }
For Claude Desktop users using another JDBC driver or a combination of drivers:
Add the following, edited to suit your local environment, to claude_desktop_config.json
:
"jdbc": { "command": "java", "args": [ "-cp", "/path/to/mcp-jdbc-server/MCPServer-1.0.0-runner.jar:/path/to/jdbc_driver1.jar:/path/to/jdbc_driverN.jar", "io.quarkus.runner.GeneratedMain" ], "env": { "jdbc.url": "jdbc:virtuoso://localhost:1111", "jdbc.user": "dba", "jdbc.password": "dba" } }
After successful installation, the following tools will be available to MCP client applications.
name descriptionjdbc_get_schemas
List database schemas accessible to connected database management system (DBMS). jdbc_get_tables
List tables associated with a selected database schema. jdbc_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. jdbc_filter_table_names
List tables, based on a substring pattern from the q
input field, associated with a selected database schema. jdbc_query_database
Execute a SQL query and return results in JSONL format. jdbc_execute_query
Execute a SQL query and return results in JSONL format. jdbc_execute_query_md
Execute a SQL query and return results in Markdown table format. jdbc_spasql_query
A Virtuoso-specific feature! Execute a SPASQL query and return results. jdbc_sparql_query
A Virtuoso-specific feature! Execute a SPARQL query and return results. jdbc_virtuoso_support_ai
A Virtuoso-specific feature! Interact with LLMs through the Virtuoso Support Assistant/Agent.
jdbc_get_schemas
user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.jdbc_get_tables
schema
(string, optional): Database schema to filter tables. Defaults to connection default.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.TABLE_CAT
, TABLE_SCHEM
, TABLE_NAME
, TABLE_TYPE
).jdbc_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.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.jdbc_describe_table
schema
(string, required): The database schema name containing the table.table
(string, required): The name of the table to describe.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.COLUMN_NAME
, TYPE_NAME
, COLUMN_SIZE
, IS_NULLABLE
).jdbc_query_database
query
(string, required): The SQL query string to execute.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.jdbc_query_database_md
query
(string, required): The SQL query string to execute.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.jdbc_query_database_jsonl
query
(string, required): The SQL query string to execute.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.jdbc_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
(i.e., 30 seconds).user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.Demo.demo.execute_spasql_query
).jdbc_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
(i.e., 30 seconds).user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string."UB".dba."sparqlQuery"
).jdbc_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"
.user
(string, optional): Database username. Defaults to "demo"
.password
(string, optional): Database password. Defaults to "demo"
.url
(string, optional): JDBC URL connection string.DEMO.DBA.OAI_VIRTUOSO_SUPPORT_AI
).For basic MCP client use and troubleshooting, use the MCP Inspector as follows:
Install the MCP Inspector:
npm install -g @modelcontextprotocol/inspector
Start the inspector:
npx @modelcontextprotocol/inspector java -jar /path/to/mcp-jdbc-server/MCPServer-1.0.0-runner.jar
Access the URL returned by the inspector to troubleshoot MCP server interactions.
MCP Inspector Connecting to additional DriversFor basic MCP client use and troubleshooting, use the MCP Inspector as follows:
Install the JDBC Driver(s), ensuring their JAR files are registered with the host operating system's Java Virtual Machine (JVM) via $CLASSPATH
. For instance:
export CLASSPATH=$CLASSPATH:/path/to/driver1.jar:/path/to/driver2.jar:/path/to/driverN.jar
Start the inspector using the following command-line arguments:
npx @modelcontextprotocol/inspector java -cp MCPServer-1.0.0-runner.jar:/path/to/driver1.jar:/path/to/driver2.jar:/path/to/driverN.jar io.quarkus.runner.GeneratedMain
Assuming the following JDBC Driver information:
Oracle JDBC Driver URL Template
jdbc:oracle:thin:@<hostname>:[port]:<SERVICEID>
Informix JDBC Driver URL Template
jdbc:informix-sqli://<hostname>:<port>/<database></database>:<INFORMIXSERVER>=<SERVICEID>
Install the Oracle (ojdbc17.jar
) and/or Informix (jdbc-15.0.0.1.1.jar
) JDBC Drivers, and ensure their JAR files are registered with the host operating system's Java Virtual Machine (JVM) via $CLASSPATH
. For instance:
export CLASSPATH=$CLASSPATH:/path/to/Java/Extensions/jdbc-15.0.0.1.1.jar export CLASSPATH=$CLASSPATH:/path/to/Java/Extensions/ojdbc17.jar
Start the inspector using the following command-line arguments:
npx @modelcontextprotocol/inspector java -cp MCPServer-1.0.0-runner.jar:/path/to/Java/Extensions/ojdbc17.jar:/path/to/Java/Extensions/jdbc-15.0.0.1.1.jar io.quarkus.runner.GeneratedMain
Access the URL returned by the inspector and then use the jdbc_execute_query
operation to query the target database, by providing actual values for the following input field templates:
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4