Backstage MCP
@iocanel
About Backstage MCP
A simple backstage mcp server using quarkus-backstage
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Backstage MCP?
Backstage MCP is an example MCP server that integrates with Backstage using the Quarkus Backstage library. It allows developers to list available Backstage templates and instantiate them from the command line via an MCP client like Goose.
How to use Backstage MCP?
You need a Backstage installation with service-to-service authentication enabled and a static token configured. The server is built with Quarkus and runs as a STDIO-based MCP server. Configure your MCP client (e.g., Goose) to execute the Quarkus application (e.g., quarkus-run.jar via jbang).
Key features of Backstage MCP
- List available Backstage templates
- Instantiate a template from the command line
Use cases of Backstage MCP
- Browse all Backstage templates via an AI agent without leaving the terminal
- Create new projects by instantiating a template using parameter values from a YAML file
FAQ from Backstage MCP
What is needed to run Backstage MCP?
A Backstage installation with service-to-service authentication enabled and a static token configured in the app configuration.
How does the server communicate with Backstage?
It uses the Quarkus Backstage library to talk to the Backstage API, and communicates with the MCP client over STDIO (reads from stdin, writes to stdout).
What can I do with Backstage MCP?
List available templates and instantiate a template by providing parameter values in a values.yaml file.
How do I set it up with Goose?
Add the server configuration to Goose’s config.yaml, specifying the path to the Quarkus application (e.g., quarkus-run.jar) and using jbang as the command.
Are there any known limitations?
The README does not mention any limitations. The server is presented as an example.
Frequently asked questions
What is needed to run Backstage MCP?
A Backstage installation with service-to-service authentication enabled and a static token configured in the app configuration.
How does the server communicate with Backstage?
It uses the Quarkus Backstage library to talk to the Backstage API, and communicates with the MCP client over STDIO (reads from stdin, writes to stdout).
What can I do with Backstage MCP?
List available templates and instantiate a template by providing parameter values in a `values.yaml` file.
How do I set it up with Goose?
Add the server configuration to Goose’s config.yaml, specifying the path to the Quarkus application (e.g., `quarkus-run.jar`) and using `jbang` as the command.
Are there any known limitations?
The README does not mention any limitations. The server is presented as an example.
Basic information
More Other MCP servers

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Codelf
unbugA search tool helps dev to solve the naming things problem.
Comments