home / mcp / azure devops mcp server

Azure DevOps MCP Server

Provides read-only access to Azure DevOps data via the MCP interface using the CData JDBC Driver.

Installation

Add the following to your MCP client configuration file.

Configuration

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

You can query live Azure DevOps data through a read-only MCP server that exposes Azure DevOps data as MCP tools. This lets large language models fetch up-to-date information without writing SQL, turning natural language questions into structured data queries behind the scenes.

How to use

Connect your MCP-enabled client to the local MCP server you run from this guide. Once running, you can ask your AI assistant questions like “What is the status of open work items in the current sprint?” or “Show recent commits in Project X.” The server presents Azure DevOps data via built-in tools that your client can call implicitly through natural language prompts. You do not need to issue raw SQL queries; simply ask for the data you want and the AI client will use the available tools to retrieve it.

How to install

# Prerequisites
- Java Runtime Environment (JRE) 11+ installed
- Git available on your system
- Maven available on your system for building the server

# 1. Clone the repository
git clone https://github.com/cdatasoftware/azure-devops-mcp-server-by-cdata.git
cd azure-devops-mcp-server-by-cdata

# 2. Build the server
mvn clean install

# This creates the JAR file: CDataMCP-jar-with-dependencies.jar

# 3. Obtain the CData JDBC Driver for Azure DevOps and install it
# (Follow the official download steps for the driver from CData)
# 4. License the CData JDBC Driver
# Windows
#   Navigate to the lib folder of the installation and run:
#   java -jar cdata.jdbc.azuredevops.jar --license
#   Enter your name, email, and license key (or TRIAL)
# Mac/Linux
#   java -jar cdata.jdbc.azuredevops.jar --license

# 5. Configure your JDBC connection to Azure DevOps
# Run the connection string utility
java -jar cdata.jdbc.azuredevops.jar
# Test the connection and copy the connection string when successful

# 6. Create a .prp file for your JDBC connection
# Example azure-devops.prp
Prefix=azuredevops
ServerName=CDataAzureDevOps
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.azuredevops.jar
DriverClass=cdata.jdbc.azuredevops.AzureDevOpsDriver
JdbcUrl=jdbc:azuredevops:InitiateOAuth=GETANDREFRESH;
Tables=

# 7. Build the MCP server JAR is already done in step 2
# Start the server using the .prp file
java -jar CDataMCP-jar-with-dependencies.jar /PATH/TO/azure-devops.prp

Additional content

Configuration notes and usage details extracted from practical setup steps include how to prepare the MCP environment, how to connect to Azure DevOps via the CData JDBC Driver, and how to run the MCP server locally. The server runs in stdio mode on the same machine as its clients, so you start it on your workstation and connect your MCP client locally.

Notes and troubleshooting

If you cannot see the MCP server in your MCP client after setup, fully quit the client and restart it to refresh the available servers. If the client cannot retrieve data, verify that the connection string is correct and that the JDBC driver is licensed and configured properly. For further help, reach out to the CData Support Team or the CData Community.

Available tools

azuredevops_get_tables

Retrieves a list of available tables (data sources) in the Azure DevOps MCP connection. Output is CSV with headers representing table names.

azuredevops_get_columns

Retrieves the list of columns for a specified table. Output is CSV with headers representing column names.

azuredevops_run_query

Executes a SQL SELECT query against the configured Azure DevOps data model and returns the results.