Measure MCP Server - Tech Preview
A Model Context Protocol (MCP) server provides a structured way for GenAI clients to access tools, data, and actions through a consistent, secure interface. When you connect a GenAI client that supports MCP to the Measure MCP server, you can use natural-language requests to retrieve information from your Measure.
This release contains access to the MCP server feature in Velocity Measure as a Tech Preview and can be enabled by passing
the betaFeature=mcp parameter while running the installer. The
Tech Preview is intended for you to view the capabilities of MCP server offered
by Velocity, and
to provide your feedback to the product team. You are permitted to use the
information only for evaluation purposes and not for use in a production
environment. IBM® provides the information without
obligation of support and "as is" without warranty of any kind.
- applicationById
- builds
- deployments
- latestWorkflowGateChecks
- metrics
- teamsForCurrentUser
- teamspacesForTenant
- workflow
- workflowsForTenant
- workflowStatsByIdQuery
To use the Measure MCP server, you must enable the MCP server feature flag when you run the installer. See Prerequisites to connect with the MCP server in Measure.
You can currently connect to the Measure MCP server using the following GenAI clients:
- Claude Desktop. See Connecting to the DevOps Velocity MCP server in Claude Desktop
- GitHub Copilot in Visual Studio Code. See Connecting to the Measure MCP server by using GitHub Copilot in Visual Studio Code.
The MCP deployment is enabled, and the MCP pod is running in the default configuration. To reduce resource consumption, you must disable the MCP deployment when the MCP server is not in use. See Disabling the MCP Deployment in DevOps Velocity.