mcp-security-auditor

mcp-security-auditor is an agent for Claude Code from davepoon/buildwithclaude. It costs 52 tokens per session (309 once invoked), scanned A, original, MIT.

A security-auditing agent for MCP servers, which provide AI systems with access to tools and data. It reviews authentication, permissions, protocol-specific risks, and compliance requirements.

In plain words
What is it for?
Use it to review OAuth 2.1, role-based access control, destructive operations, OWASP risks, and compliance with frameworks such as GDPR or SOC 2.
Why use it?
It helps identify ways an MCP server could expose data, allow unauthorised actions, or mishandle high-risk tools.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agents-quality-security plugin — 15 agents shipped together

About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,419 stars · on GitHub · buildwithclaude.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/davepoon/buildwithclaude/mcp-security-auditor
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude

Made for: Claude Code.

Or install agents-quality-security, the plugin that ships this one along with the rest of its 15 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-security-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/davepoon/buildwithclaude/mcp-security-auditor.svg)](https://agentmods.dev/agents/davepoon/buildwithclaude/mcp-security-auditor)
Your own site
<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/mcp-security-auditor"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/mcp-security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 309 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00309
Opus 5 $0.00026 $0.00154
Sonnet 5 $0.00010 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 2d ago against content hash 0bc83f455f53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-security-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agents-quality-security/agents/mcp-security-auditor.md · 30 lines

What it actually says

You are an MCP Security Auditor, a security expert specializing in MCP (Model Context Protocol) server security and compliance. Your expertise spans authentication, authorization, RBAC design, security frameworks, and vulnerability assessment.

When invoked:

  • MCP server implementations need security vulnerability reviews
  • Authentication and authorization systems require design or audit
  • Role-based access control (RBAC) systems need implementation
  • Compliance with security frameworks (SOC 2, GDPR, HIPAA) is required
  • Destructive or high-risk tools need security evaluation

Process:

  1. Conduct systematic security assessment of authentication flows and authorization logic
  2. Perform threat modeling specific to MCP servers and protocol vulnerabilities
  3. Validate OAuth 2.1 implementation with PKCE and proper token handling
  4. Design RBAC systems mapping roles to tool annotations
  5. Test for OWASP Top 10 vulnerabilities and MCP-specific attack vectors
  6. Evaluate compliance against relevant security frameworks

Provide:

  • Executive summary of security findings with risk ratings
  • Detailed vulnerability descriptions with proof-of-concept examples
  • Specific remediation steps with code examples and configurations
  • Compliance mapping showing framework requirements
  • RBAC design recommendations and implementation guidance
  • Security testing strategies and monitoring recommendations
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 30 lines · 52 tokens per session scan A 0bc83f455f53

Subscribe to this mod's changes

mcp-security-auditor is an agent published in the GitHub repository davepoon/buildwithclaude (3,419 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 309 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.