Back to Home
n0zer0d4y icon

athena-protocol

Verified Safe

by n0zer0d4y

Overview

An intelligent MCP server that acts as an AI tech lead for coding agents, providing expert validation, impact analysis, and strategic guidance before code changes are made.

Installation

Run Command
npx @n0zer0d4y/athena-protocol

Environment Variables

  • DEFAULT_LLM_PROVIDER
  • PROVIDER_SELECTION_PRIORITY
  • <PROVIDER_NAME>_API_KEY
  • <PROVIDER_NAME>_MODEL
  • <PROVIDER_NAME>_TEMPERATURE
  • <PROVIDER_NAME>_MAX_TOKENS
  • <PROVIDER_NAME>_TIMEOUT
  • LLM_TEMPERATURE_DEFAULT
  • LLM_MAX_TOKENS_DEFAULT
  • LLM_TIMEOUT_DEFAULT
  • OPENAI_MAX_COMPLETION_TOKENS_DEFAULT
  • OPENAI_VERBOSITY_DEFAULT
  • OPENAI_REASONING_EFFORT_DEFAULT
  • TOOL_CALLING_READ_FILE_ENABLED
  • TOOL_CALLING_SEARCH_FILES_ENABLED
  • TOOL_CALLING_LIST_FILES_ENABLED
  • TOOL_CALLING_WRITE_TO_FILE_ENABLED
  • TOOL_CALLING_REPLACE_IN_FILE_ENABLED
  • TOOL_CALLING_EXECUTE_COMMAND_ENABLED
  • TOOL_CALLING_MAX_FILE_SIZE_KB
  • TOOL_CALLING_MAX_EXECUTION_TIME_SEC
  • TOOL_CALLING_ALLOWED_FILE_EXTENSIONS
  • TOOL_CALLING_ALLOWED_COMMANDS
  • TOOL_TIMEOUT_THINKING_VALIDATION_MS
  • TOOL_TIMEOUT_IMPACT_ANALYSIS_MS
  • TOOL_TIMEOUT_ASSUMPTION_CHECKER_MS
  • TOOL_TIMEOUT_DEPENDENCY_MAPPER_MS
  • TOOL_TIMEOUT_THINKING_OPTIMIZER_MS
  • NODE_ENV
  • DEBUG
  • CONFIG_UNIFIED
  • CONNECTION_POOL_ENABLED
  • CONNECTION_POOL_MAX_CONNECTIONS
  • CONNECTION_POOL_KEEP_ALIVE
  • CLIENT_CACHE_ENABLED
  • CLIENT_CACHE_TTL
  • CLIENT_MAX_CACHE_SIZE
  • ENV_CACHE_TTL
  • MEMORY_MAX_SHORT_TERM_ENTRIES
  • MEMORY_MAX_PERSISTENT_ENTRIES
  • MEMORY_COMPRESSION_THRESHOLD
  • MEMORY_RELEVANCE_THRESHOLD
  • LOG_ENABLED
  • LOG_LEVEL
  • LOG_PATH

Security Notes

The server enables execution of shell commands (`executeShell`) and Git operations (`gitOperation`) via internal tools. While `executeShell` is safeguarded by a strict whitelist (`TOOL_CALLING_ALLOWED_COMMANDS`) and explicit `enabled` flag (default true), `gitOperation` does not appear to have the same whitelist validation applied directly within the `ToolCallingService` before execution. File writing (`writeFile`) and editing (`editFile`) are disabled by default (`TOOL_CALLING_WRITE_TO_FILE_ENABLED=false`, `TOOL_CALLING_REPLACE_IN_FILE_ENABLED=false`), which is a critical security measure. The `README.md` explicitly warns about the 'CRITICAL RISK' of `executeCommand` and encourages careful whitelisting. No hardcoded sensitive secrets are present in the core server, with API keys managed through environment variables. The test project's intentional flaws (e.g., multiple JWT secrets) are confined to test infrastructure and not the MCP server itself.

Similar Servers

Stats

Interest Score29
Security Score7
Cost ClassHigh
Avg Tokens15000
Stars5
Forks2
Last Update2026-01-04

Tags

mcpai-agentthinking-validationcode-reviewimpact-analysis