Skip to main content
Glama
Red Hat API MCP Server

Red Hat API MCP Server

by fnarel

Red Hat API MCP Server

Python 3.13+ MCP Compatible UV

Fork of judexzhu/redhat-api-mcp with additional calls.

This project implements a Model Context Protocol (MCP) server that provides tools for interacting with Red Hat APIs, making it easy to integrate with LLM applications.

Table of Contents

Related MCP server: Redmine MCP Server

Features

The server exposes the following Red Hat API tools:

  1. Search Red Hat KCS Solutions - Search for knowledge base solutions

  2. Get Solution by ID - Retrieve full solution content

  3. Search Red Hat Cases - Find cases matching a query

  4. Get Case Details - Retrieve detailed information about a specific case

Prerequisites

  • Python 3.13 or higher

  • UV package manager (recommended Python package manager)

  • Red Hat API offline token (obtained from your Red Hat account)

Installation

1. Install UV (if not already installed)

2. Clone and Setup Project

git clone https://github.com/fnarel/hydra-mcp-server.git
cd hydra-mcp-server
uv sync

Configuration

1. Get Your Red Hat API Token

  1. Visit the Red Hat API Token Management page per KCS

  2. Log in to your Red Hat account

  3. Generate an offline token

  4. Copy and save the token securely

2. Environment Setup

Create a .env file in the project root with your Red Hat API token:

# Create .env file
echo "RH_API_OFFLINE_TOKEN=your_offline_token_here" > .env

Replace your_offline_token_here with your actual offline token from step 1.

Usage

Developing with the MCP Inspector

You can test the server using the MCP development tools:

uv run mcp dev redhat_mcp_server.py

This will start the MCP inspector, allowing you to interact with your tools interactively.

Integrating with Claude Desktop

To install the server in Claude Desktop, add this configuration to your Claude Desktop config file.

{
  "mcpServers": {
    "redhat": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/redhat-api-mcp",
        "run",
        "redhat_mcp_server.py"
      ],
      "env": {
        "RH_API_OFFLINE_TOKEN": "your_actual_offline_token_here"
      }
    }
  }
}

Available Tools

search_kcs

Search for Red Hat KCS Solutions and Articles.

search_kcs(query: str, rows: int = 50, start: int = 0) -> List[Dict]

Parameters:

  • query (str): Search terms (supports advanced Solr syntax)

  • rows (int, optional): Number of results to return (default: 50, max: 100)

  • start (int, optional): Starting index for pagination (default: 0)

Returns: List of solution objects with id, title, score, and view_uri

get_kcs

Get a Red Hat solution by its ID and extract structured content.

get_kcs(solution_id: str) -> Dict

Parameters:

  • solution_id (str): The KCS solution ID

Returns: Dictionary with title, environment, issue, resolution, and root_cause

search_cases

Search for Red Hat support cases.

search_cases(query: str, rows: int = 10, start: int = 0) -> List[Dict]

Parameters:

  • query (str): Search terms

  • rows (int, optional): Number of results to return (default: 10)

  • start (int, optional): Starting index for pagination (default: 0)

Returns: List of case objects with case_number, summary, status, product, etc.

get_case

Get detailed information about a specific Red Hat support case.

get_case(case_number: str) -> Dict

Parameters:

  • case_number (str): The Red Hat case number (e.g., "01234567")

Returns: Detailed case information with summary, description, severity, and comments

Advanced Usage

Advanced Query Parameters

For detailed information about using advanced Solr query expressions with the Red Hat Hydra API, see expression.md.

Prompt Templates

The server includes sophisticated prompt templates for case analysis:

  • Case Summary: Generates C.A.S.E. format summaries

  • Case Resolution: Provides investigation workflows

  • Multi-phase Analysis: Advanced case resolution protocols

Custom Configuration

You can override default API endpoints by adding these to your .env file:

# Optional: Custom API endpoints
RH_API_BASE_URL=https://access.redhat.com
RH_SSO_URL=https://sso.redhat.com/auth/realms/redhat-external/protocol/openid-connect/token

License

This project is licensed under the MIT License - see the LICENSE file for details.


Note: This MCP server requires a valid Red Hat account and API access. Ensure you have the appropriate permissions for the Red Hat services you intend to access.

Available Tools

5 tools
get_caseA

Get case details by case number.

Args: case_number: The case number (e.g., "01234567")

Returns: Formatted case data with description, severity, issue, case number, and comments

Inputs: case_number (required).

get_case_rawA

Get ALL raw fields from a case for debugging/discovery.

Args: case_number: The case number (e.g., "01234567")

Returns: The complete unfiltered API response with all available fields

Inputs: case_number (required).

get_kcsA

Get a specific solution by ID and extract structured content

Args: solution_id: The ID of the solution to retrieve

Returns: Dictionary with title, Environment, Issue, Resolution, and Root Cause

Inputs: solution_id (required).

search_casesB

Search for Red Hat cases and return a list of case numbers.

Args: query: Search query string rows: Number of results to return (default: 10) start: Starting index for pagination (default: 0)

Returns: List of cases with their numbers and metadata

Inputs: query (required), rows, start.

search_kcsA

Search for Red Hat KCS Solutions and return a list with Solution IDs.

Args: query: Search query string rows: Number of results to return (default: 50) start: Starting index for pagination (default: 0)

Returns: List of solutions with their IDs and metadata

By default, this tool returns only documents where documentKind is either "Article" or "Solution" and accessState is either "active" or "private".

Inputs: query (required), rows, start.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: search and retrieve for KCS solutions and cases, with get_case_raw explicitly for raw debugging access. No two tools have overlapping purposes.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern using snake_case (search_kcs, get_kcs, search_cases, get_case, get_case_raw). The modifier 'raw' logically extends get_case.

    Tool Count5/5

    Five tools provide a focused surface for Red Hat support knowledge and case retrieval, neither bloated nor sparse. Each tool serves a clear purpose in the workflow.

    Completeness5/5

    The tool set covers the complete read lifecycle for both KCS solutions (search, get by ID) and support cases (search, get details, raw access), with no obvious missing operations for a read-only support API.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      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.
      -
    • A
      license
      B
      quality
      D
      maintenance
      MCP server for Redmine project management, enabling tools for managing projects, issues, users, time entries, groups, memberships, versions, wiki, news, attachments, search, and Agile sprints via the Redmine REST API.
      89
      14 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A comprehensive MCP server suite for Red Hat's automation ecosystem, enabling AI assistants to interact with Ansible Automation Platform, Event-Driven Ansible, ansible-lint, and official Red Hat documentation with secure domain validation.
      35
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that enables AI agents to interact with Red Hat OpenShift AI environments, providing tools for project management, workbench operations, model serving, and more.
      295 PyPI
      10
      Apache 2.0