Errata Tool MCP Server
FastMCP server that enables AI assistants to integrate with Red Hat Errata Tool, allowing access to product information and advisory details through authenticated API calls.
README
Errata Tool MCP Server
FastMCP server for Red Hat Errata Tool integration with AI assistants.
Quick Start
# 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'))"
Available Functions
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 accessget_advisory_info(advisory_id)- Get advisory details ⚠️ Requires auth
MCP Client Configuration
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" }
}
}
}
Authentication
For advisory access, run inside container:
kinit your_username@IPA.REDHAT.COM
Troubleshooting
| Issue | Fix |
|---|---|
| "Pigeon crap. Did it forget to run kinit?" | Run kinit inside container |
| Container won't start | Check: podman --version, ./build-container.sh logs |
| SSE connection fails | Verify: curl http://localhost:8000/sse/ |
| Products/States work but advisories don't | Run kinit for authentication |
Commands
./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 all
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.