What is mcp2agy-scan?

A security scanner that examines source code for possible vulnerabilities, including how data moves through the program and how risky operations are used. Static analysis checks code without running it.

Scanning code for issues such as remote code execution, privilege escalation, authentication bypasses, server-side request forgery, and other vulnerability classes.

It helps find potentially dangerous code paths early and records suspected issues in a structured format for later checking.

mcp2agy-scan — Skill for Claude Code and Codex by uziii2208/mcp2agy

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.

Any agent

npx skills add uziii2208/mcp2agy --skill scan

Clone the repo

git clone --depth 1 https://github.com/uziii2208/mcp2agy

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/uziii2208/mcp2agy/scan/github.svg)](https://agentmods.dev/skills/uziii2208/mcp2agy/scan)

Your own site

<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/scan"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/scan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/uziii2208/mcp2agy/scan"><img src="https://agentmods.dev/badge/skills/uziii2208/mcp2agy/scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,364 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.02364
Opus 5.5	$0.00031	$0.00946
Sonnet 5.5	$0.00016	$0.00473
Haiku 4.5	$0.00008	$0.00236

Measured 2mo ago against content hash 88b6e6b5d000, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp2agy-scan scanned grade A with 1 finding 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Pattern**: Unsafe object merging (`merge`, `deepmerge`, `Object.assign`) without `hasOwnProperty` checks, or `child_process.exec()` with template strings.

.agents/plugins/mcp2agy/skills/scan/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/scan — 0day Vulnerability Scanner & Subagent (v3.0.0)

0. Prime Directive & Operating Modes

Audit FIRST for what kills (P0: RCE, PrivEsc, Sandbox Escape, Auth Bypass), THEN for what hurts (P1: TOCTOU, SSRF, OOM, Desync), THEN for what annoys (P2/P3). Every finding must be grounded in actual code — never fabricate.

Operating Modes:

Subagent Mode (Delegated by Orchestrator):
- Receives target files and run ID from the parent agent.
- Executes triage scan and writes structured findings to mcp2agy_workspace/auditor_zone/results/<run_id>/candidates.yaml.
- Sends a structured summary back to the Orchestrator.
Standalone Mode (CLI /scan <path>):
- Performs scan on <path>, outputs candidate findings to terminal, and saves candidates to mcp2agy_workspace/auditor_zone/results/latest/candidates.yaml.

1. Candidate Record Schema (`candidates.yaml`)

Every candidate must adhere to this exact schema. Downstream Verifier subagents will reject malformed candidates at Gate 1:

---CANDIDATE---
id: CAND-<run_id>-<seq>
priority: P0 | P1 | P2 | P3
cwe_candidates: [CWE-N, ...]
vuln_class: <named class from taxonomy>
file: <absolute or workspace-relative path>
file_hash: <sha256 of file>
line_count: <total lines in file>
line_range: [N, M]
function: <function or method name>
short_description: <one line describing the defect>
source_input: <what attacker controls: HTTP param, CLI arg, wire data, tool arg>
intermediate_hops: [<func1>, <func2>, ...]
sink_effect: <what happens at the dangerous sink>
preconditions_claimed:
  auth: none | guest | user | admin
  network_position: internet | lan | localhost | mitm
  ui_interaction: none | click | run_cmd | paste | dropfile
  timing_race: none | milliseconds | seconds
  config_default: yes | no
chain_candidate: yes | no
chain_partner_hint: <CAND-id or null>
---END-CANDIDATE---

2. Vulnerability Hunting Playbook (2026 Calibrated)

2.1 🔴 P0 — Critical Priority (Audit These First)

Read the full file on GitHub · 184 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.

2mo ago First seen · 184 lines · 78 tokens per session scan A 88b6e6b5d000

Subscribe to this mod's changes

mcp2agy-scan is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 2,364 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

mcp2agy-scan