Scan a page for broken (4xx/5xx/timeout) links. Returns a summary and the list of broken URLs
AI agents call check_broken_links to retrieve information from ToolCenter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only audit of HTTP link status codes on a page. It retrieves and reports information about link health without creating, modifying, deleting, or executing any operations. The output is a summary of existing link status — purely observational. No side effects or state changes result from its use.
From the tool's definition Tool name 'check_broken_links' and description 'Scan a page for broken (4xx/5xx/timeout) links. Returns a summary and the list of broken URLs' indicate purely informational retrieval with no modification or deletion of data.
Attacks that exploit this kind of access
Scan a page for broken (4xx/5xx/timeout) links. Returns a summary and the list of broken URLs. It is categorised as a Read tool in the ToolCenter MCP MCP Server, which means it retrieves data without modifying state.
Register the ToolCenter MCP server in PolicyLayer and add a rule for check_broken_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 ToolCenter MCP. Nothing to install.
check_broken_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_broken_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_broken_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_broken_links is provided by the ToolCenter MCP server (toolcenter-dev/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 →