列出 GitHub 仓库中的文件和目录。当需要浏览 GitHub 仓库内容时使用此工具。我会自动从配置文件读取 token 和代理设置。
AI agents call github_ls to retrieve information from MCP Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool lists repository contents without creating, modifying, or deleting data. It is a pure read operation that retrieves information about a repository structure. The 'ls' (list) operation is inherently non-destructive and has no side effects beyond information retrieval. Severity is low because misuse results only in unauthorized viewing of repository metadata, not data loss or system compromise.
From the tool's definition Tool name 'github_ls' and description '列出 GitHub 仓库中的文件和目录' (list files and directories in GitHub repository) indicates a listing/browsing operation with no modification capability.
Attacks that exploit this kind of access
列出 GitHub 仓库中的文件和目录。当需要浏览 GitHub 仓库内容时使用此工具。我会自动从配置文件读取 token 和代理设置。. It is categorised as a Read tool in the MCP Toolkit MCP Server, which means it retrieves data without modifying state.
Register the MCP Toolkit MCP server in PolicyLayer and add a rule for github_ls: 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 MCP Toolkit. Nothing to install.
github_ls 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 github_ls 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 github_ls. 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.
github_ls is provided by the MCP Toolkit MCP server (zxfgds/mcp-toolkit). 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 →