Extract links from a page and check each for broken responses (4xx/5xx).
AI agents call check_links to retrieve information from SiteHealth MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs passive reconnaissance by following links and reading HTTP response codes. It retrieves information about link health without altering any data, executing commands, or triggering side effects. This is clearly a Read operation—similar to audit tools that inspect and report on system state without changing it.
From the tool's definition Tool description states 'Extract links from a page and check each for broken responses (4xx/5xx).' This is a retrieval and status-checking operation with no modification, deletion, code execution, or financial impact.
Attacks that exploit this kind of access
Extract links from a page and check each for broken responses (4xx/5xx). It is categorised as a Read tool in the SiteHealth MCP MCP Server, which means it retrieves data without modifying state.
Register the SiteHealth MCP server in PolicyLayer and add a rule for 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 SiteHealth MCP. Nothing to install.
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 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 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.
check_links is provided by the SiteHealth MCP server (sitehealth-mcp). 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 →