home / mcp / jira mcp server

Jira MCP Server

This read-only MCP Server allows you to connect to Jira data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-jira-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/jira.prp"
      ]
    }
  }
}

You can query Jira live data with a read-only MCP server that wraps the CData JDBC Driver for Jira. This server exposes Jira as MCP endpoints so you can ask natural-language questions and receive up-to-date results without writing SQL. It’s ideal for AI assistants that need Jira data in real time while staying safely read-only.

How to use

Once the MCP server is running, you can interact with it through an MCP-compatible client to read data from Jira. Use natural language prompts to ask questions like the status of issues, open tickets, or Jira project details. The built-in tools expose available data structures and allow you to list tables, inspect columns, and run read-only queries. You don’t need to write SQL to retrieve information; the client translates your questions into data queries transparently.

How to install

Prerequisites you need before installing: - Java Runtime Environment (JRE) or JDK that can run the MCP server jar - Git and Maven (for building from source) if you choose to compile locally - A Jira data source configured through the CData JDBC Driver for Jira and a valid Jira connection string

Step 1: Build the MCP server (from source) - Clone the repository - Build the project to produce the MCP jar ``bash git clone https://github.com/cdatasoftware/jira-mcp-server-by-cdata.git cd jira-mcp-server-by-cdata mvn clean install`This creates the MCP jar namedCDataMCP-jar-with-dependencies.jar`.

Step 2: Install the CData JDBC Driver for Jira - Download and install the driver from the CData site - License the driver by running in the driver’s lib directory: ``bash java -jar cdata.jdbc.jira.jar --license`` Enter your name, email, and the license key (or TRIAL).

Step 3: Configure the Jira connection - Run the Connection String utility to test and copy the connection string ``bash java -jar cdata.jdbc.jira.jar`` Follow the prompts and click Test Connection. If OAuth is used, complete authentication in your browser.

Step 4: Create a .prp file for the JDBC connection (example content shown) ``env Prefix=jira ServerName=CDataJIRA ServerVersion=1.0 DriverPath=PATH\TO\cdata.jdbc.jira.jar DriverClass=cdata.jdbc.jira.JIRADriver JdbcUrl=jdbc:jira:InitiateOAuth=GETANDREFRESH; Tables=`Save this asjira.prp`.

Step 5: Start the MCP server using the generated PRP file ``bash java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/jira.prp`` This launches the MCP server in stdio mode, which works with clients on the same machine.

Additional configuration and usage notes

Claude Desktop or another MCP client can be configured to load the Jira MCP server by adding an entry that runs the MCP jar with the PRP file. For Claude Desktop, place the MCP server configuration in your MCP server list and provide the Java command and the path to the PRP file.

Troubleshooting

If you cannot see your MCP server in your client, ensure you have fully exited and restarted the MCP client. If data cannot be retrieved, re-check the connection string in the PRP file and re-test the connection. For persistent issues, contact CData Support or join the CData Community for help.

License

This MCP server is licensed under the MIT License. You may use, modify, and distribute it in compliance with the terms of MIT.

Tools & Descriptions

The server exposes a set of read-only tools to discover and query Jira data. Each tool is named after the MCP server and a function, enabling you to explore the Jira data model and run practical queries.

Usage examples in practice

Typical questions you can ask include: - What is the state of open Jira issues in a specific project? - How many issues are in the DONE status across teams? - Which issues are assigned to a particular user and are due soon?

Available tools

jira_get_tables

Retrieves a list of accessible Jira data tables. The output is CSV with headers in the first line.

jira_get_columns

Retrieves the list of columns for a specific Jira table. The output is CSV with headers in the first line.

jira_run_query

Executes a read-only SQL SELECT query against Jira data exposed by the MCP server.