What is mcp-agent-review CLAUDE.md?

Repository instructions for mcp-agent-review, an MCP server that exposes a code-review tool. They describe installation, tests, architecture, environment settings, and how review context is collected.

Use them when developing or testing the server, its review pipeline, safety checks, or the external OpenAI-compatible model integration.

They give an agent the project’s expected build, test, and review behavior so changes can be checked consistently.

How lzx1413/mcp-agent-review configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lzx1413/mcp-agent-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lzx1413/mcp-agent-review/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lzx1413/mcp-agent-review

Made for: Claude Code.

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/instructions/lzx1413/mcp-agent-review/claude-md/github.svg)](https://agentmods.dev/instructions/lzx1413/mcp-agent-review/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lzx1413/mcp-agent-review/claude-md"><img src="https://agentmods.dev/badge/instructions/lzx1413/mcp-agent-review/claude-md/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/instructions/lzx1413/mcp-agent-review/claude-md"><img src="https://agentmods.dev/badge/instructions/lzx1413/mcp-agent-review/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 679 This file is loaded in full into every session.

When invoked 679 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00679	$0.00679
Opus 5	$0.00340	$0.00340
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 10d ago against content hash e1173b012247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-agent-review CLAUDE.md 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 10d 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.

CLAUDE.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Run

pip install -e .              # install in editable mode
pip install -e ".[dev]"       # install with test dependencies
mcp-agent-review               # run the MCP server (entry point)

Testing

pytest                        # run all tests
pytest tests/test_tools.py    # run a single test file
pytest -k "TestSafeResolve"   # run a specific test class
pytest -k "test_path_traversal_blocked"  # run a single test

Tests use monkeypatch to stub get_git_root and git utility functions — no real git repo or API calls are needed. The conftest.py autouse fixture strips all API-related env vars.

Architecture

This is an MCP server that exposes a single tool (review_code) to Claude Code. The review is performed by an external OpenAI-compatible model (not Claude itself), which gets agentic tool access to investigate the repo.

Review pipeline (server.py → reviewer.py):

Collect context: git diff, changed file contents (with ±50-line padding around hunks), CLAUDE.md, git log
Build system prompt via build_system_prompt() — injects task_description (developer intent) and review_focus (directed dimension) when provided
Send to OpenAI-compatible model with tool definitions, loop up to MAX_TOOL_ROUNDS (default 8) letting the model call tools
Run a self-critique pass (second model call) to filter low-confidence findings
Parse JSON output into formatted findings

Key modules:

server.py — FastMCP server setup, review_code tool registration, orchestrates the pipeline
reviewer.py — builds the user message, runs the agentic tool loop, self-critique, and output formatting
tools.py — defines GPT_TOOLS (OpenAI function-calling schema) and execute_tool_call dispatcher; tools: read_file, grep_code, git_blame, list_files, search_git_history, find_test_files
git_utils.py — git operations (diff, log, blame), diff parsing, changed-file context extraction with range merging
prompts.py — build_system_prompt() dynamically assembles the system prompt (base + optional developer intent / directed focus sections), plus self-critique prompt

Read the full file on GitHub · 47 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.

10d ago First seen · 47 lines · 679 tokens per session scan A e1173b012247

Subscribe to this mod's changes

mcp-agent-review CLAUDE.md is an instructions file published in the GitHub repository lzx1413/mcp-agent-review (1 stars, last pushed 4mo ago), licensed MIT. It adds 679 tokens to every session, about $0.0034 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 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-agent-review: Instructions file for Claude Code