All servers · Databases · Maps, location & weather

io.github.BenAHammond/code-auditor-mcp

io.github.BenAHammond/code-auditor-mcp · v5.0.2

Has write/delete tools

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Has destructive tools (destructiveHint)
Capabilities declared	tools
Tool definitions	4 tools · with description 100% · input schema is an object 100% · read/destructive hints 100%

Enforces architectural invariants and code quality rules inside your AI agent's edit loop.

streamable-http · https://www.codeauditormcp.com/api/mcp

claude mcp add --transport http code-auditor-mcp https://www.codeauditormcp.com/api/mcp

{
  "mcpServers": {
    "code-auditor-mcp": {
      "url": "https://www.codeauditormcp.com/api/mcp"
    }
  }
}

get_install_commands
Return the exact install commands for Code Auditor for a given AI agent. Call this when a user asks how to install Code Auditor, or asks for the command for a specific agent (claude, cursor, codex, gemini, agents, zcode, or all).
lookup_rule
Return the rule kind, description, default severity, detection method, and threshold for a given Code Auditor rule or analyzer. Call this when a user asks what a specific rule does (e.g. import-ban, sql-injection, n+1).
explain_symptom
Map a natural-language symptom (e.g. 'my app is slow', 'hardcoded password', 'infinite react loop') to the relevant Code Auditor rule(s) and their fixes. Call this when a user describes a problem rather than naming a rule.
request_rule write/delete
Request a new Code Auditor rule. Call lookup_rule or explain_symptom first to confirm no existing rule covers it. Provide a minimal example that should be flagged and a corrected example that should not. Reduce both to the smallest code that shows the difference, and remove secrets and proprietary i

Repository · JSON · Text for agents · Registry updated 2026-10-10