AI agents call md_check_links to retrieve information from LuzzyTool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs link validation by checking HTTP status and accessibility of URLs referenced in Markdown files. This is a passive read operation with no side effects—it retrieves status information about links without creating, modifying, or deleting data, and does not execute arbitrary code or perform financial transactions. It falls squarely into the Read category.
From the tool's definition Tool checks validity of links in Markdown documents ('检查 Markdown 中的链接有效性' = 'check link validity in Markdown'). This is a read/verification operation that examines URLs without modifying content or executing code.
Attacks that exploit this kind of access
【Markdown】检查 Markdown 中的链接有效性。. It is categorised as a Read tool in the LuzzyTool MCP Server, which means it retrieves data without modifying state.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for md_check_links: 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 LuzzyTool. Nothing to install.
md_check_links 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 md_check_links 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 md_check_links. 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.
md_check_links is provided by the LuzzyTool MCP server (luzzymeow/luzzytool). 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 →