azerothMCP
Verified Safeby blinkysc
Overview
Provides AI assistants (like Claude) with read-only access to AzerothCore databases, wiki, and game mechanics for AI-powered assistance in game development and analysis.
Installation
python main.pyEnvironment Variables
- DB_HOST
- DB_PORT
- DB_USER
- DB_PASSWORD
- DB_WORLD
- DB_CHARACTERS
- DB_AUTH
- READ_ONLY
- ENABLE_SPELL_DBC
- ENABLE_VISUALIZATION
- ENABLE_WIKI
- ENABLE_SOURCE_CODE
- WIKI_PATH
- AZEROTHCORE_SRC_PATH
- MCP_PORT
- SOAP_ENABLED
- SOAP_HOST
- SOAP_PORT
- SOAP_USERNAME
- SOAP_PASSWORD
- SOAP_TIMEOUT
- ENABLE_SANDBOX
- LOG_TOOL_CALLS
- LOG_LEVEL
- MAPS_PATH
- VIZ_HOST
- VIZ_PORT
Security Notes
The server features a 'sandbox' tool (`execute_investigation`) which directly executes Python code (`exec`) provided by the AI. While extensive `FORBIDDEN_PATTERNS` and `SAFE_BUILTINS` are implemented to restrict capabilities (e.g., no `import`, `open`, `eval`, `exec` inside the sandbox itself, and SQL queries are restricted to read-only `SELECT`, `SHOW`, `DESCRIBE`), the presence of `exec` always carries inherent risk. By default, database operations are read-only (`READ_ONLY=true`), and optional features like source code/wiki search and SOAP commands are disabled, significantly reducing the attack surface. Users enabling write access or other optional features must exercise caution.
Similar Servers
context7
Context7 MCP enhances LLM prompts by injecting up-to-date, version-specific documentation and code examples directly from source code, enabling more accurate and relevant code generation.
unity-mcp
MCP for Unity acts as a bridge, allowing AI assistants to interact directly with the Unity Editor to manage assets, control scenes, edit scripts, and automate tasks.
mcp
Provides AI assistants with direct, real-time access to official Microsoft Learn documentation to prevent hallucinations and retrieve accurate technical information.
docs-mcp-server
The Documentation MCP Server indexes documentation from various sources (web, local files, registries) and makes it semantically searchable via vector embeddings, primarily for AI coding assistants.