Skip to main content
AI
  • Get started with AI

    • Red Hat AI

      Accelerate the development and deployment of enterprise AI solutions.

    • AI learning hub

      Explore learning materials and tools, organized by task.

    • AI interactive demos

      Click through scenarios with Red Hat AI, including training LLMs and more.

    • AI/ML learning paths

      Expand your Red Hat OpenShift AI knowledge using these learning resources.

    • AI quickstarts

      Focused AI use cases designed for fast deployment on Red Hat AI platforms.

    • No-cost AI training

      Foundational Red Hat AI training.

  • Featured resources

    • Red Hat OpenShift AI
    • Open source AI for developers
    • AI product application development
    • Open source-powered AI/ML for hybrid cloud
    • AI and Node.js cheat sheet

Red Hat AI Factory with NVIDIA

Red Hat AI Factory with NVIDIA is a co-engineered, enterprise-grade AI solution for building, deploying, and managing AI at scale across hybrid cloud environments.

Learn
  • Self-guided

    • Documentation

      Find answers, get step-by-step guidance, and learn how to use Red Hat products.

    • Learning paths

      Explore curated walkthroughs for common development tasks.

    • Guided learning

      Receive custom learning paths powered by our AI assistant.

    • See all learning
  • Hands-on

    • Developer Sandbox

      Spin up Red Hat's products and technologies without setup or configuration.

    • Interactive labs

      Learn by doing in these hands-on, browser-based experiences.

    • Interactive demos

      Click through product features in these guided tours.

  • Browse by topic

    • AI/ML
    • Automation
    • Java
    • Kubernetes
    • Linux
    • See all topics
  • Training & certifications

    • Courses and exams
    • Certifications
    • Skills assessments
    • Red Hat Academy
    • Learning subscription
    • Explore training
Build
  • Get started

    • Red Hat build of Podman Desktop

      A downloadable, local development hub to experiment with our products and builds.

    • Developer Sandbox

      Spin up Red Hat's products and technologies without setup or configuration.

  • Download products

    • Red Hat Enterprise Linux
    • Red Hat AI
    • Red Hat OpenShift
    • Red Hat Ansible Automation Platform
    • See all products
  • Featured

    • Red Hat build of OpenJDK
    • Red Hat JBoss Enterprise Application Platform
    • Red Hat OpenShift Dev Spaces
    • Red Hat Developer Toolset
  • References

    • E-books
    • Documentation
    • Cheat sheets
    • Architecture center
Community
  • Get involved

    • Events
    • Live AI events
    • Red Hat Summit
    • Red Hat Accelerators
    • Community discussions
  • Follow along

    • Articles & blogs
    • Developer newsletter
    • Videos
    • Github
  • Get help

    • Customer service
    • Customer support
    • Regional contacts
    • Find a partner

Join the Red Hat Developer program

Download Red Hat products and project builds, access support documentation, learning content, and more.

ConsoleDocsSupport Search
New For you

Recommended

We'll recommend resources you may like as you browse. Try these suggestions for now.

  • Product downloads
  • Cheat sheets
  • Red Hat Developer learning portal
  • Developer blog
  • E-books
  • Developer Sandbox
Log in

Get more with a Red Hat Developer account

  • Product downloads
  • Console access
  • Event registration
  • Training & trials
Explore more account benefitsLog in or register

A subscription may be required for some services.

Contact us

MCP in Red Hat Developer Hub: Chat with your catalog

November 10, 2025
John Collier
Related topics:
APIsArtificial intelligenceDeveloper productivityIntegrationPlatform engineering
Related products:
Red Hat Developer HubRed Hat Plug-ins for Backstage

    This article outlines new plug-ins for Red Hat Developer Hub that provides tools for MCP (Model Context Protocol) clients to interact with it. Starting in version 1.8, you can install plug-ins from the Extensions Marketplace that provide an MCP server in Developer Hub, along with tools that allow MCP clients to query the contents of the software catalog and retrieve TechDocs documentation associated with catalog entities.

    Red Hat Developer Hub is an internal developer platform (IDP) based on Backstage. It helps development teams and organizations increase productivity by centralizing information from many sources into a single portal. For example, Red Hat Developer Hub provides a software catalog that acts as a central location for the components, APIs, and documentation an organization uses to build software. 

    Model Context Protocol provides a standard for connecting AI models and applications (MCP clients) to external systems and tools (MCP servers). This connection allows them to access information on those systems. MCP servers expose "tools"—a set of actions that can be executed against those external systems. You can write MCP servers for almost any purpose; there are MCP tools for querying weather information, web searches, file systems, and more. 

    Introducing MCP tool plug-ins for Red Hat Developer Hub

    Recently, the Backstage project introduced a new plug-in for Backstage that implements an MCP server, based on the Actions Registry. This allows IDPs, such as Red Hat Developer Hub, to easily define MCP tools in a Backstage-native way using simple back-end plug-ins, which removes the need to build a separate MCP server. Instead, you simply build a back-end plug-in that defines a basic action. 

    At Red Hat, we recently investigated what effective MCP tools for Developer Hub would look like. We decided on the following as a starting point:

    • The tools should be able to query the entire software catalog, including the detailed metadata.
    • The tools should be able to retrieve documentation (TechDocs) known to the instance.
    • The tools should focus on read-only operations as a starting point. Write or potentially destructive operations require further security considerations.

    As a result, we developed two separate MCP tool plug-ins that can be installed alongside the Backstage MCP server:

    • software-catalog-mcp-tool
    • techdocs-mcp-tool

    Next, let's look at how to enable those plug-ins and what they can do.

    Install the MCP server plug-ins

    Prerequisites:

    • Red Hat Developer Hub 1.8

    To enable the MCP server and tools in Developer Hub, update your dynamic-plugins.yaml configuration to add the following plug-ins:

           # MCP server backend plugin
           - package: oci://ghcr.io/redhat-developer/rhdh-plugin-export-overlays/backstage-plugin-mcp-actions-backend:bs_1.42.5__0.1.2!backstage-plugin-mcp-actions-backend
             disabled: false
          
           # MCP tools plugins
           - package: oci://ghcr.io/redhat-developer/rhdh-plugin-export-overlays/red-hat-developer-hub-backstage-plugin-software-catalog-mcp-tool:bs_1.42.5__0.2.3!red-hat-developer-hub-backstage-plugin-software-catalog-mcp-tool
             disabled: false
           - package: oci://ghcr.io/redhat-developer/rhdh-plugin-export-overlays/red-hat-developer-hub-backstage-plugin-techdocs-mcp-tool:bs_1.42.5__0.3.0!red-hat-developer-hub-backstage-plugin-techdocs-mcp-tool
             disabled: false

    Then, update the app-config to configure a static token for authentication:

     backend: 
       auth:
         externalAccess:
           - type: static
             options:
               token: ${MCP_TOKEN}
               subject: mcp-clients

    Finally, update the app-config to specify which MCP tools you would like to enable:

     backend:
       actions:
         pluginSources:
           - software-catalog-mcp-tool
           - techdocs-mcp-tool

    Configure your MCP client application

    Prerequisites: 

    • Red Hat Developer Hub 1.8 with the MCP plug-ins installed
    • A compatible MCP client

    Once you've installed the MCP plug-ins in your Developer Hub instance, it's easy to connect MCP client applications to it.

    The following sections detail configurations for common clients to use with the MCP tools.

    Cursor

    Add the following to ~/.cursor/mcp.json (or, alternatively, go to Cursor Settings → Tools and MCP and click New MCP Server) and paste the following, substituting the values for ${RHDH_HOST} and ${STATIC_TOKEN}:

    {
     "mcpServers": {
       "backstage-actions": {
         "url": "${RHDH_HOST}/api/mcp-actions/v1",
         "headers": {
           "Authorization": "Bearer ${STATIC_TOKEN}"
         }
       }
     }
    }

    Continue

    If you have an agent.yaml configured for continue.dev, and the following to the bottom of it to allow it to use the MCP server, substituting the values for ${RHDH_HOST} and ${STATIC_TOKEN}:

    mcpServers:
     - name: backstage-actions
       type: streamable-http
       url: ${RHDH_HOST}/api/mcp-actions/v1
       requestOptions:
         headers:
           Authorization: "Bearer ${STATIC_TOKEN}"

    Claude CLI

    Run the following command, substituting the values for ${RHDH_HOST} and ${STATIC_TOKEN}:

    claude mcp add backstage_mcp "${RHDH_HOST}/api/mcp-actions/v1" --transport http -H "Authorization: <static token>"

    Then, confirm that it shows up when you run claude mcp list:

    Checking MCP server health...
    backstage_mcp: https://${RHDH_HOST}/api/mcp-actions/v1 (HTTP) - ✓ Connected

    Using the tools

    So what can the tools do? Here's a breakdown with some example tool calls.

    Software Catalog MCP tool

    As mentioned earlier, we wanted a way for AI models to interact with the software catalog. We created a basic MCP tool here that can retrieve any entity from the catalog, along with its metadata. In addition, there are optional parameters for filtering your query by entity kind, type, owner, and tags. 

    You can use basic queries to get any information about a specific entity you want to know more about, as illustrated in Figure 1:

    Fetch beneficiary management API catalog entry.
    An AI application executing the query "Get information about the `beneficiary-management-api` component". It found and returned a single component matching that name.
    Figure 1: Query and response for fetching the beneficiary-management-api catalog entry.

    Or you can use it to find the catalog entry you need, if you're not certain about specifics (Figure 2):

    Find all catalog entries that contain metadata about transactions
    An AI application executing the MCP tool, returning entities that match the word "transaction."
    Figure 2: Query and response for finding all catalog entries that contain metadata about transactions.

    Finally, you can even string together multiple tool calls using a single query (Figure 3):

    Get the API entity that the "beneficiary-management-api" component exposes (verbose: true), and from that, retrieve the OpenAPI spec. Then using the OpenAPI spec, construct a curl command to add a new beneficiary
    The AI app executing the query.
    Figure 3: A query with multiple tool calls.

    Figure 4 shows the response.

    The result of the query, with the AI application summarizing the API specification, and providing an example curl command to run.
    Figure 4: The AI application executing the preceding query.

    TechDocs MCP tools

    We also wanted MCP clients to be able to query information about documentation associated with catalog entries.

    For example, you can inquire about which entities in the catalog have documentation and documentation coverage (see Figure 5):

    What percentage of entities in the catalog have documentation?
    An AI application executes the query "What percentage of entities in the catalog have documentation." It shows the model calling the TechDocs tool, and returning how much coverage there is.
    Figure 5: Query and response for "What percentage of entities in the catalog have documentation?"

    You can even query for documentation about specific entities or ask how certain entities work, as shown in Figures 6 and 7:

    How does the audio-to-text software template work? 
    The execution of an MCP tool, showing multiple tool calls retrieving information about the "audio-to-text" software template.
    Figure 6: Query for "How does the audio-to-text software template work?" and multiple tool calls retrieving information about the audio-to-text software template.

    The result is shown in Figure 7.

    The result of the MCP tool execution, showing a summary of the "audio-to-text" software template's documentation.
    Figure 7: Summarizing the audio-to-text software template's documentation.

    Conclusion

    MCP creates opportunities to integrate AI models with existing systems and services, with Backstage serving as a crucial platform. The new MCP plug-ins in Red Hat Developer Hub showcase the advantages of connecting your developer portal with AI clients and use the new MCP server that Backstage now provides. 

    You'll be able to try it before month's end on Red Hat Developer Hub 1.8 or on Red Hat Developer Hub Local!

    Learn more:

    • How to build a simple agentic AI server with MCP
    • A quick look at MCP with large language models and Node.js
    • LLMs and Red Hat Developer Hub: How to catalog AI assets
    • How to template AI software in Red Hat Developer Hub 

    Recent Posts

    • A day in the life of an NVIDIA H100 on Red Hat OpenShift 5

    • Migrate BuildConfigs to builds for Red Hat OpenShift with one plug-in install

    • Run Red Hat Enterprise Linux CoreOS on NVIDIA BlueField DPUs

    • Agent harness engineering: Separating model capabilities from enforcement

    • What's new for developers in Red Hat Enterprise Linux 10.3 and 9.9

    What’s up next?

    Writing “Hello, World” hasn’t gotten any harder, but running it has. Download our developer’s guide to developer portals to learn how engineering teams can reduce friction and boost productivity using internal developer portals (IDPs).

    Get the e-book
    Red Hat Developers logo

    Platforms

    • Red Hat AI
    • Red Hat Enterprise Linux
    • Red Hat OpenShift
    • Red Hat Ansible Automation Platform
    • See all products

    Build

    • Developer Sandbox
    • Developer tools
    • Interactive tutorials
    • API catalog

    Quicklinks

    • Learning resources
    • E-books
    • Cheat sheets
    • Blog
    • Events
    • Newsletter

    Communicate

    • About us
    • Contact sales
    • Find a partner
    • Report a website issue
    • Site status dashboard
    • Report a security problem

    Red Hat Developer

    Build here. Go anywhere.

    We serve the builders. The problem solvers who create careers with code.

    Join us if you’re a developer, software engineer, web designer, front-end designer, UX designer, computer scientist, architect, tester, product manager, project manager or team lead.

    Sign me up

    Red Hat legal and privacy links

    • About Red Hat
    • Jobs
    • Events
    • Locations
    • Contact Red Hat
    • Red Hat Blog
    • Inclusion at Red Hat
    • Cool Stuff Store
    • Red Hat Summit
    © 2026 Red Hat

    Red Hat legal and privacy links

    • Privacy statement
    • Terms of use
    • All policies and guidelines
    • Digital accessibility
    Ask AI