mcp-implementation-security-review

mcp-implementation-security-review is a skill for Claude Code, Codex from drvoss/everything-copilot-cli. It costs 58 tokens per session (1,826 once invoked), scanned A, original, MIT.

A source-code security review for an MCP server or client, where MCP is a protocol for connecting AI assistants to tools and data. It checks implementation details such as authentication, sessions, rate limits, input schemas, and SDK use, with file and line references.

In plain words
What is it for?
It is for reviewing custom MCP implementations, security-sensitive pull requests, third-party MCP source code, and internal wrappers around MCP software libraries.
Why use it?
It helps uncover exploitable flaws in how the MCP connection and tool dispatch are built, rather than only checking configuration.

Skill for Claude CodeCodex

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 skills/drvoss/everything-copilot-cli/mcp-implementation-security-review
Any agent
npx skills add drvoss/everything-copilot-cli --skill mcp-implementation-security-review
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Claude Code, Codex.

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-implementation-security-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/mcp-implementation-security-review.svg)](https://agentmods.dev/skills/drvoss/everything-copilot-cli/mcp-implementation-security-review)
Your own site
<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/mcp-implementation-security-review"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/mcp-implementation-security-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00058 $0.01826
Opus 5 $0.00029 $0.00913
Sonnet 5 $0.00012 $0.00365
Haiku 4.5 $0.00006 $0.00183

Measured today against content hash 7bd1682c4c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-implementation-security-review 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 today.

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.

skills/security/mcp-implementation-security-review/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Implementation Security Review

Review the source code of an MCP server or client implementation for exploitable vulnerabilities. This is a code-level review — it inspects how a server or client is built, not how it is configured or governed. Every finding must be backed by a file/line citation so the report is directly actionable.

When to Use

  • A team is shipping or accepting a custom MCP server/client implementation (not just an off-the-shelf binary)
  • Code review of a PR that adds or modifies MCP transport, auth, or tool-dispatch logic
  • Before trusting a third-party MCP server whose source is available for inspection
  • Auditing an internal MCP SDK wrapper for unsafe defaults

When NOT to Use

Instead of mcp-implementation-security-review Use
Verifying plugin/package integrity and pinned versions (no source review) agent-supply-chain
Broad OWASP Agentic Security Initiative Top 10 audit across the whole agent pipeline agent-owasp-check
Configuring .mcp.json for a server you are not modifying mcp-ecosystem
Building a brand-new MCP server from scratch mcp-builder (pair this skill in afterward)

This skill overlaps deliberately little with agent-supply-chain (package/version integrity) and agent-owasp-check (OWASP ASI Top 10 across the whole agent pipeline): both of those treat the MCP server as a black box. This skill opens the box and reviews the implementation itself.

Prerequisites

  • Read access to the MCP server or client's actual source code (not just its manifest)
  • Know the transport in use: stdio, HTTP+SSE, or streamable HTTP
  • Know the SDK/language the implementation uses (affects which unsafe patterns apply)

The Five Controls

Review each control in the implementation source, not just its documentation:

Control What to inspect
Authentication How the server verifies caller identity; whether unauthenticated tool calls are possible; token validation logic
Session management Session ID generation (must be cryptographically random, not sequential/timestamp-based); session fixation and hijack resistance; expiry enforcement
Rate limiting Per-tool and per-session throttling; whether a single caller can exhaust server resources or downstream APIs
Schema validation Whether every tool input is validated against a strict schema before use, or passed through to shell/SQL/filesystem calls unchecked
SDK usage Whether the implementation uses the official MCP SDK's safe primitives correctly, or reimplements transport/framing logic in a way that reintroduces known SDK-fixed bugs

Read the full file on GitHub · 161 lines

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. today First seen · 161 lines · 58 tokens per session scan A 7bd1682c4c51

Subscribe to this mod's changes

mcp-implementation-security-review is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 1,826 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.

Related

Other skills, from other repositories

winui-design

Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…

microsoft/win-dev-skills · 119 tokens

winui-dev-workflow

Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.

microsoft/win-dev-skills · 73 tokens

winui-packaging

MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…

microsoft/win-dev-skills · 86 tokens

winui-session-report

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

microsoft/win-dev-skills · 61 tokens

microsoft-build

Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessions, and plan your event schedule. Activate when users mention sessions, schedule, what's new, Build, Ignite, AI Tour, Microsoft event, conference, or…

microsoft/Build-CLI · 109 tokens

journey-template

Create new agentic journeys from app ideas. Generates README.md (learner walkthrough), PLAN.md (AI-readable spec), and app-specific skills for OSS deployments. Supports any stack (Node.js, Python, .NET, Java, Swift, Kotlin) and Azure service (Container Apps, AKS, Functions, App Service). USE FOR: new journey, scaffold…

DanWahlin/github-azure-agentic-journeys · 153 tokens