Fetch a URL and grade its HTTP security headers (CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, COOP/CORP). Pass url. Returns a letter grade + score, present/missing headers, and a per-header analysis with the live value and issues. Also flags Server/X-Po...
AI agents call security.http-headers to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval only—it fetches and analyzes HTTP headers from a target URL without side effects. The action is read-only (GET request to examine headers), non-destructive, and produces only an analysis report. SSRF guards prevent abuse against internal networks. No data is created, modified, deleted, or financial operations are triggered.
From the tool's definition Tool fetches a URL and grades HTTP security headers, returning analysis of header presence, values, and issues.
Attacks that exploit this kind of access
Fetch a URL and grade its HTTP security headers (CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, COOP/CORP). Pass url. Returns a letter grade + score, present/missing headers, and a per-header analysis with the live value and issues. Also flags Server/X-Powered-By info disclosure. SSRF-guarded live fetch (private targets refused) — an LLM can. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for security.http-headers: 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. Nothing to install.
security.http-headers 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 security.http-headers 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 security.http-headers. 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.
security.http-headers is provided by the MCP server (@2sio/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 →