AI agents call http_headers to retrieve information from MCP Recon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
HTTP header retrieval is a read-only operation that gathers publicly available metadata from web servers. It has no capability to modify, delete, execute code, or move money. The tool belongs in the reconnaissance family (passive information gathering) and poses minimal risk as it only retrieves existing data. Severity is low because the information obtained is typically non-sensitive metadata.
From the tool's definition Tool name 'http_headers' indicates retrieval of HTTP response headers from a web server. No description provided, but the name and context within a reconnaissance server strongly suggest this is a passive information gathering operation that queries and…
Documented attack patterns abuse exactly the kind of access http_headers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Recon, and nothing reaches the server without passing your rules. This is the rule we recommend for http_headers:
{
"version": "1",
"default": "deny",
"tools": {
"http_headers": {}
}
}http_headers is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
http_headers. It is categorised as a Read tool in the MCP Recon MCP Server, which means it retrieves data without modifying state.
Register the MCP Recon MCP server in PolicyLayer and add a rule for 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 Recon. Nothing to install.
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 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 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.
http_headers is provided by the MCP Recon MCP server (sundayz-hunter/mcp_recon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Recon, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 MCP Recon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.