Provides integration with Red Hat Errata Tool, allowing querying of products, advisory states, listing advisories, and fetching advisory details with proper authentication.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Errata Tool MCP Server show me the details for advisory 149143"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FastMCP server for Red Hat Errata Tool integration with AI assistants.
# Build and run
./build-container.sh build
./build-container.sh run-sse
# Get interactive shell with working Kerberos
./build-container.sh interactive
kinit your_username@IPA.REDHAT.COM
# Test functions
python -c "from mcp_server import list_products; print(list_products())"
python -c "from mcp_server import get_advisory_info; print(get_advisory_info('149143'))"Related MCP server: Red Hat Lightspeed MCP
list_products() - List available products (RHEL, RHIVOS, etc.)
list_states() - List advisory states (QE, SHIPPED_LIVE, etc.)
list_advisories(product, state, limit) - List advisories ⚠️ Limited access
get_advisory_info(advisory_id) - Get advisory details ⚠️ Requires auth
Add to your MCP client config (e.g., ~/.cursor/mcp.json):
{
"mcpServers": {
"errata-tool": {
"command": "podman",
"args": ["run", "-d", "--rm", "--name", "errata-mcp-sse", "-p", "8000:8000",
"-v", "/etc/krb5.conf:/etc/krb5.conf:ro", "--network", "host",
"localhost/errata-mcp:latest"],
"transport": { "type": "sse", "url": "http://localhost:8000" }
}
}
}For advisory access, run inside container:
kinit your_username@IPA.REDHAT.COMIssue | Fix |
"Pigeon crap. Did it forget to run kinit?" | Run |
Container won't start | Check: |
SSE connection fails | Verify: |
Products/States work but advisories don't | Run |
./build-container.sh build # Build image
./build-container.sh run-sse # Run SSE server (port 8000)
./build-container.sh run-stdio # Run stdio mode (for MCP clients)
./build-container.sh interactive # Open bash shell with working Kerberos
./build-container.sh shell # Get shell in running container
./build-container.sh logs # View logs
./build-container.sh stop # Stop containers
./build-container.sh clean # Remove allThis server cannot be deployed
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
MCP server for AI access to Swagger by SmartBear.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
