Allows querying and accessing data from Amazon DynamoDB through a simple MCP interface using natural language questions instead of SQL.
Enables access to data stored in Amazon S3 buckets through natural language queries without requiring SQL knowledge.
Provides read-only access to Asana data by exposing it as a relational SQL model accessible through natural language queries.
Allows read-only access to Basecamp data through natural language queries rather than SQL.
Enables querying BigCommerce data through natural language rather than direct SQL queries.
Provides access to Bitbucket data by exposing it as a relational SQL model queryable through natural language.
Allows querying Box data through natural language questions instead of SQL commands.
Enables access to Confluence data through natural language queries without requiring SQL knowledge.
Provides read-only access to Couchbase data by exposing it as a relational SQL model accessible via natural language.
Allows querying Databricks data through natural language questions rather than writing SQL.
Enables read-only access to Dropbox data through natural language queries rather than SQL commands.
Provides access to eBay data through natural language queries without requiring SQL knowledge.
Allows querying Elasticsearch data through natural language rather than complex query syntax.
Enables read-only access to EnterpriseDB data by exposing it as a relational SQL model.
Provides access to Facebook data through natural language queries without requiring SQL knowledge.
Allows querying GitHub data by exposing it as a relational SQL model accessible through natural language.
Enables read-only access to Gmail data through natural language queries rather than SQL commands.
Provides access to Google Ads data through natural language queries without requiring SQL knowledge.
Allows querying Google Analytics data through natural language questions rather than SQL.
Enables read-only access to Google Calendar data through natural language queries.
Provides access to Google Campaign Manager 360 data through natural language queries.
Allows querying Google Cloud Storage data through natural language rather than SQL.
Enables read-only access to Google Drive data through natural language queries.
Provides access to Google Sheets data through natural language queries without requiring SQL knowledge.
Allows querying GraphQL endpoints through natural language questions rather than GraphQL syntax.
Enables read-only access to Greenhouse data through natural language queries.
Provides access to HubSpot data through natural language queries without requiring SQL knowledge.
Allows querying Instagram data through natural language questions rather than SQL.
Enables read-only access to Jira data through natural language queries rather than SQL commands.
Allows querying MailChimp data through natural language questions rather than SQL.
Enables read-only access to MariaDB databases through natural language queries.
Provides access to MongoDB data by exposing it as a relational SQL model queryable through natural language.
Allows querying MYOB AccountRight data through natural language rather than SQL.
Enables read-only access to MySQL databases through natural language queries rather than SQL commands.
Provides access to Neo4J graph databases through natural language queries without requiring SQL knowledge.
Allows querying Odoo data through natural language questions rather than SQL.
Enables read-only access to Okta data through natural language queries.
Provides access to PayPal data through natural language queries without requiring SQL knowledge.
Allows querying Pinterest data through natural language questions rather than SQL.
Enables read-only access to PostgreSQL databases through natural language queries rather than SQL commands.
Provides access to Presto data through natural language queries without requiring SQL knowledge.
Allows querying QuickBooks data through natural language questions rather than SQL.
Enables read-only access to Redis data through natural language queries.
Provides access to RSS feeds through natural language queries without requiring SQL knowledge.
Allows querying various Sage products (Sage 200, 300, 50 UK, Cloud Accounting, Intacct) through natural language.
Enables read-only access to Salesforce data through natural language queries rather than SQL commands.
Provides access to various SAP products through natural language queries without requiring SQL knowledge.
Allows querying SendGrid data through natural language questions rather than SQL.
Enables read-only access to Shopify data through natural language queries.
Provides access to SingleStore databases through natural language queries without requiring SQL knowledge.
Allows querying Slack data through natural language questions rather than SQL.
Enables read-only access to Snapchat Ads data through natural language queries.
Provides access to Snowflake data through natural language queries without requiring SQL knowledge.
Allows querying Splunk data through natural language questions rather than Splunk's search syntax.
Enables read-only access to Square data through natural language queries.
Provides access to Stripe data through natural language queries without requiring SQL knowledge.
Allows querying SurveyMonkey data through natural language questions rather than SQL.
Enables read-only access to Teradata databases through natural language queries.
Provides access to Trello data through natural language queries without requiring SQL knowledge.
Allows querying Trino data through natural language questions rather than SQL.
Enables read-only access to Twilio data through natural language queries.
Provides access to WooCommerce data through natural language queries without requiring SQL knowledge.
Allows querying WordPress data through natural language questions rather than SQL.
Enables read-only access to Xero accounting data through natural language queries.
Provides access to XML data sources through natural language queries without requiring SQL knowledge.
Allows querying YouTube Analytics data through natural language questions rather than SQL.
Enables read-only access to Zendesk data through natural language queries.
Provides access to various Zoho products (Books, Creator, CRM, Inventory, Projects) through natural language queries.
ibm-db2-mcp-server-by-cdata
CData's Model Context Protocol (MCP) Server for IBM DB2
: This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free [CData MCP Server for IBM DB2 (beta)](https://www.cdata.com/download/download.aspx?sku=EDZK-V &type=beta).
Purpose
We created this read-only MCP Server to allow LLMs (like Claude Desktop) to query live data IBM DB2 supported by the CData JDBC Driver for IBM DB2.
CData JDBC Driver connects to IBM DB2 by exposing them as relational SQL models.
This server wraps that driver and makes IBM DB2 data available through a simple MCP interface, so LLMs can retrieve live information by asking natural language questions — no SQL required.
Setup Guide
- Clone the repository:
- Build the server:This creates the JAR file: CDataMCP-jar-with-dependencies.jar
- Download and install the CData JDBC Driver for {source}: https://www.cdata.com/drivers/db2/download/jdbc
- License the CData JDBC Driver:
- Navigate to the
lib
folder in the installation directory, typically:- (Windows)
C:\Program Files\CData\CData JDBC Driver for IBM DB2\
- (Mac/Linux)
/Applications/CData JDBC Driver for IBM DB2/
- (Windows)
- Run the command
java -jar cdata.jdbc.db2.jar --license
- Enter your name, email, and "TRIAL" (or your license key).
- Navigate to the
- Configure your connection to the data source (Salesforce as an example):
- Run the command
java -jar cdata.jdbc.db2.jar
to open the Connection String utility. - Configure the connection string and click "Test Connection"
Note: If the data sources uses OAuth, you will need to authenticate in your browser.
- Once successful, copy the connection string for use later.
- Run the command
- Create a
.prp
file for your JDBC connection (e.g.ibm-db2.prp
) using the following properties and format:- Prefix - a prefix to be used for the tools exposed
- ServerName - a name for your server
- ServerVersion - a version for your server
- DriverPath - the full path to the JAR file for your JDBC driver
- DriverClass - the name of the JDBC Driver Class (e.g. cdata.jdbc.db2.DB2Driver)
- JdbcUrl - the JDBC connection string to use with the CData JDBC Driver to connect to your data (copied from above)
- Tables - leave blank to access all data, otherwise you can explicitly declare the tables you wish to create access for
Using the Server with Claude Desktop
- Create the config file for Claude Desktop ( claude_desktop_config.json) to add the new MCP server, using the format below. If the file already exists, add the entry to the
mcpServers
in the config file. WindowsLinux/MacIf needed, copy the config file to the appropriate directory (Claude Desktop as the example). WindowsLinux/Mac - Run or refresh your client (Claude Desktop).
Note: You may need to fully exit or quit your Claude Desktop client and re-open it for the MCP Servers to appear.
Running the Server
- Run the follow the command to run the MCP Server on its own
Usage Details
Once the MCP Server is configured, the AI client will be able to use the built-in tools to read, write, update, and delete the underlying data. In general, you do not need to call the tools explicitly. Simply ask the client to answer questions about the underlying data system. For example:
- "What is the correlation between my closed won opportunities and the account industry?"
- "How many open tickets do I have in the SUPPORT project?"
- "Can you tell me what calendar events I have today?"
The list of tools available and their descriptions follow:
Tools & Descriptions
In the definitions below, {servername}
refers to the name of the MCP Server in the config file (e.g. {classname_dash}
above).
{servername}_get_tables
- Retrieves a list of tables available in the data source. Use the{servername}_get_columns
tool to list available columns on a table. The output of the tool will be returned in CSV format, with the first line containing column headers.{servername}_get_columns
- Retrieves a list of columns for a table. Use the{servername}_get_tables
tool to get a list of available tables. The output of the tool will be returned in CSV format, with the first line containing column headers.{servername}_run_query
- Execute a SQL SELECT query
Troubleshooting
- If you cannot see your CData MCP Server in Claude Desktop, be sure that you have fully quit Claude Desktop (Windows: use the Task Manager, Mac: use the Activity Monitor)
- If Claude Desktop is unable to retrieve data, be sure that you have configured your connection properly. Use the Connection String builder to create the connection string (see above) and copy the connection string into the property (.prp) file.
- If you are having trouble connecting to your data source, contact the CData Support Team.
- If you are having trouble using the MCP server, or have any other feedback, join the CData Community.
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
All Supported Sources
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
IBM DB2 MCP Server by CData
Related MCP Servers
- -securityAlicense-qualityMariaDB MCP Server by CDataLast updated -MIT License
- -securityAlicense-qualityIBM Informix MCP Server by CDataLast updated -MIT License
- -securityAlicense-qualityBox MCP Server by CDataLast updated -MIT License
- -securityAlicense-qualityMySQL MCP Server by CDataLast updated -1MIT License