【核心工具】审查整个项目的代码。适用于跨文件夹修改、系统级重构或需要全面上下文的情况。Codex 将分析项目结构和代码，根据提供的变更描述进行审查和修复。
AI agents call review_project to retrieve information from Codex MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite operating on an entire project, review_project is fundamentally a Read operation. It retrieves and analyzes project structure and code to provide review feedback and suggestions. The tool does not execute code, delete files, create modifications, or commit changes—it inspects and reports.
From the tool's definition Tool description indicates it 'reviews' (审查) the project code and 'analyzes' (分析) project structure and code. The core operation is examining and assessing code without modifying it.
Attacks that exploit this kind of access
【核心工具】审查整个项目的代码。适用于跨文件夹修改、系统级重构或需要全面上下文的情况。Codex 将分析项目结构和代码，根据提供的变更描述进行审查和修复。. It is categorised as a Read tool in the Codex MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Codex MCP Server MCP server in PolicyLayer and add a rule for review_project: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Codex MCP Server. Nothing to install.
review_project is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the review_project rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for review_project. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
review_project is provided by the Codex MCP Server MCP server (spongebaby-124/codexreviewermcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →